AlphaGaO commited on
Commit
aaa1d03
·
verified ·
1 Parent(s): da80088

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen3-8B
4
+ tags:
5
+ - text-generation-inference
6
+ - transformers
7
+ - qwen3
8
+ - ui-generation
9
+ - tailwind-css
10
+ - html
11
+ language:
12
+ - en
13
+ ---
14
+
15
+ # UIGEN-T3 — Advanced UI Generation with Hybrid Reasoning
16
+
17
+ > Tesslate’s next-gen UI model, built for thoughtful design.
18
+
19
+ ---
20
+
21
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/fqZE717ubrgSpAOHeMEeQ.png" alt="UIGEN-T3 UI Screenshot 1" width="500">
22
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/N5gfKRD-j9JAeMoGy7O3K.png" alt="UIGEN-T3 UI Screenshot 2" width="500">
23
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/PDGXycDkVsxFRxqHc6TKD.png" alt="UIGEN-T3 UI Screenshot 2" width="500">
24
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/Q4CHYYcDAN60NFjIPVQnH.png" alt="UIGEN-T3 UI Screenshot 3" width="500">
25
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/ePZoCA8lS4Y1KdkchrTlQ.png" alt="UIGEN-T3 UI Screenshot 4" width="500">
26
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/BU-Pk2moNsTOGuYF1XuRx.png" alt="UIGEN-T3 UI Screenshot 5" width="500">
27
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/64d1129297ca59bcf7458d07/gz5ub0lDpS-hhw1MB7e07.png" alt="UIGEN-T3 UI Screenshot 6" width="500">
28
+
29
+ ## Demos
30
+
31
+ Explore New UI generations:
32
+ 📂 [https://uigenoutput.tesslate.com](https://uigenoutput.tesslate.com)
33
+
34
+ ---
35
+
36
+ **Join our Discord:** [https://discord.gg/GNbWAeJ4](https://discord.gg/GNbWAeJ4)
37
+ **Our Website:** [https://tesslate.com](https://tesslate.com)
38
+
39
+ ## Quick Information
40
+
41
+ * **UI generation model** built on **Qwen3 architecture**
42
+ * Supports both **components** and **full web pages**
43
+ * **Hybrid reasoning system**: Use `/think` or `/no_think` modes
44
+ * Powered by **UIGenEval**, a first-of-its-kind benchmark for UI generation
45
+ * Released for **research, non-commercial use.** If you want to use it commercially, please contact us for a pilot program.
46
+
47
+ ---
48
+
49
+ ## Model Details
50
+
51
+ * **Base Model**: Qwen/Qwen3-8B
52
+ * **Reasoning Style**: Hybrid (`/think` and `/no_think`)
53
+ * **Tokenizer**: Qwen default, with design token headers
54
+ * **Output**: Components + Full pages (with `<html>`, `<head>`)
55
+ * **Images**: User-supplied or placehold.co – no images in the dataset due to licensing concerns.
56
+ * **License**: Research only (non-commercial). Contact us for enterprise use cases.
57
+
58
+ ---
59
+
60
+ ## Reasoning System
61
+
62
+ UIGEN-T3 was trained using a **pre/post reasoning model architecture**.
63
+
64
+ You can explicitly control the reasoning mode:
65
+
66
+ * `/think` → Enables guided reasoning with layout analysis and heuristics.
67
+ * `/no_think` → Faster, raw code generation.
68
+
69
+ Outputs also include **design tokens** at the top of each generation for easier site-wide customization.
70
+
71
+ ---
72
+
73
+ ## Inference Parameters
74
+
75
+ Please use 20k context length to get the best results if using reasoning.
76
+
77
+ | Parameter | Value |
78
+ | :---------- | :---- |
79
+ | Temperature | 0.6 |
80
+ | Top P | 0.95 |
81
+ | Top K | 20 |
82
+ | Max Tokens | 40k+ |
83
+
84
+ ---
85
+
86
+ ## Evaluation: UIGenEval Framework
87
+
88
+ **UIGenEval** is our internal evaluation suite, designed to **bridge the gap** between creative output and quality assurance.
89
+ *(Learn more in our upcoming paper: "UIGenEval: Bridging the Evaluation Gap in AI-Driven UI Generation" - August, 2025)*
90
+
91
+ UIGenEval evaluates models across four pillars:
92
+
93
+ 1. **Technical Quality** — Clean HTML, CSS structure, semantic accuracy.
94
+ 2. **Prompt Adherence** — Feature completeness and fidelity to instructions.
95
+ 3. **Interaction Behavior** — Dynamic logic hooks and functional interactivity.
96
+ 4. **Responsive Design** — Multi-viewport performance via Lighthouse, Axe-core, and custom scripts.
97
+
98
+ This comprehensive framework directly informs our **GRPO reward functions** for the next release.
99
+
100
+ ---
101
+
102
+ ## Example Prompts to Try
103
+
104
+ * `make a google drive clone`
105
+ * `build a figma-style canvas with toolbar`
106
+ * `create a modern pricing page with three plans`
107
+ * `generate a mobile-first recipe sharing app layout`
108
+
109
+ ---
110
+
111
+ ## Use Cases
112
+
113
+ | Use Case | Description |
114
+ | :---------------------- | :-------------------------------------------------------------------------- |
115
+ | **Startup MVPs** | Quickly scaffold UIs from scratch with clean code. |
116
+ | **Design-to-Code Transfer** | Figma (coming soon) → Code generation. |
117
+ | **Component Libraries** | Build buttons, cards, navbars, and export at scale. |
118
+ | **Internal Tool Builders** | Create admin panels, dashboards, and layout templates. |
119
+ | **Rapid Client Prototypes** | Save time on mockups with production-ready HTML+Tailwind outputs. |
120
+
121
+ ---
122
+
123
+ ## Limitations
124
+
125
+ * No Bootstrap support (planned).
126
+ * Not suited for production use — **research-only license**.
127
+ * Responsive tuning varies across output complexity.
128
+
129
+ ---
130
+
131
+ ## Roadmap
132
+
133
+ | Milestone | Status |
134
+ | :-------------------------- | :----- |
135
+ | Launch Tesslate Designer | 2 days |
136
+ | Figma convert | |
137
+ | Bootstrap & JS logic | |
138
+ | GRPO fine-tuning | |
139
+ | 4B draft model release | Now |
140
+
141
+ ---
142
+
143
+ ## Technical Requirements
144
+
145
+ * **GPU**: ≥16GB VRAM for 8B inference on GGUF.
146
+ * **Libraries**: `transformers`, `torch`, `peft`.
147
+ * Compatible with Hugging Face inference APIs and local generation pipelines.
148
+
149
+ ---
150
+
151
+ ## Community & Contribution
152
+
153
+ * **Join our Discord:** [https://discord.gg/GNbWAeJ4](https://discord.gg/GNbWAeJ4)
154
+ * Chat about AI, design, or model training.
155
+ * Want to contribute UIs or feedback? Let’s talk!
156
+
157
+ ---
158
+
159
+ ## Citation
160
+
161
+ ```bibtex
162
+ @misc{tesslate_UIGEN-T3,
163
+ title={UIGEN-T3: Hybrid Reasoning for Robust UI Generation on Qwen3},
164
+ author={Tesslate Team},
165
+ year={2025},
166
+ publisher={Tesslate},
167
+ note={Non-commercial Research License},
168
+ url={https://huggingface.co/tesslate/UIGEN-T3}
169
+ }
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for forward_message in messages %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- set message = messages[index] %}
21
+ {%- set current_content = message.content if message.content is not none else '' %}
22
+ {%- set tool_start = '<tool_response>' %}
23
+ {%- set tool_start_length = tool_start|length %}
24
+ {%- set start_of_message = current_content[:tool_start_length] %}
25
+ {%- set tool_end = '</tool_response>' %}
26
+ {%- set tool_end_length = tool_end|length %}
27
+ {%- set start_pos = (current_content|length) - tool_end_length %}
28
+ {%- if start_pos < 0 %}
29
+ {%- set start_pos = 0 %}
30
+ {%- endif %}
31
+ {%- set end_of_message = current_content[start_pos:] %}
32
+ {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
33
+ {%- set ns.multi_step_tool = false %}
34
+ {%- set ns.last_query_index = index %}
35
+ {%- endif %}
36
+ {%- endfor %}
37
+ {%- for message in messages %}
38
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
39
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
40
+ {%- elif message.role == "assistant" %}
41
+ {%- set content = message.content %}
42
+ {%- set reasoning_content = '' %}
43
+ {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
44
+ {%- set reasoning_content = message.reasoning_content %}
45
+ {%- else %}
46
+ {%- if '</think>' in message.content %}
47
+ {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
48
+ {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
49
+ {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- if loop.index0 > ns.last_query_index %}
53
+ {%- if loop.last or (not loop.last and reasoning_content) %}
54
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
55
+ {%- else %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content }}
57
+ {%- endif %}
58
+ {%- else %}
59
+ {{- '<|im_start|>' + message.role + '\n' + content }}
60
+ {%- endif %}
61
+ {%- if message.tool_calls %}
62
+ {%- for tool_call in message.tool_calls %}
63
+ {%- if (loop.first and content) or (not loop.first) %}
64
+ {{- '\n' }}
65
+ {%- endif %}
66
+ {%- if tool_call.function %}
67
+ {%- set tool_call = tool_call.function %}
68
+ {%- endif %}
69
+ {{- '<tool_call>\n{"name": "' }}
70
+ {{- tool_call.name }}
71
+ {{- '", "arguments": ' }}
72
+ {%- if tool_call.arguments is string %}
73
+ {{- tool_call.arguments }}
74
+ {%- else %}
75
+ {{- tool_call.arguments | tojson }}
76
+ {%- endif %}
77
+ {{- '}\n</tool_call>' }}
78
+ {%- endfor %}
79
+ {%- endif %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- elif message.role == "tool" %}
82
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
83
+ {{- '<|im_start|>user' }}
84
+ {%- endif %}
85
+ {{- '\n<tool_response>\n' }}
86
+ {{- message.content }}
87
+ {{- '\n</tool_response>' }}
88
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- endif %}
91
+ {%- endif %}
92
+ {%- endfor %}
93
+ {%- if add_generation_prompt %}
94
+ {{- '<|im_start|>assistant\n' }}
95
+ {%- if enable_thinking is defined and enable_thinking is false %}
96
+ {{- '<think>\n\n</think>\n\n' }}
97
+ {%- endif %}
98
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "head_dim": 128,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 12288,
13
+ "max_position_embeddings": 40960,
14
+ "max_window_layers": 36,
15
+ "model_type": "qwen3",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 151654,
20
+ "quantization_config": {
21
+ "bits": 4,
22
+ "checkpoint_format": "gptq",
23
+ "desc_act": true,
24
+ "group_size": 128,
25
+ "lm_head": false,
26
+ "meta": {
27
+ "damp_auto_increment": 0.0025,
28
+ "damp_percent": 0.01,
29
+ "mse": 0.0,
30
+ "quantizer": [
31
+ "gptqmodel:2.2.0"
32
+ ],
33
+ "static_groups": false,
34
+ "true_sequential": true,
35
+ "uri": "https://github.com/modelcloud/gptqmodel"
36
+ },
37
+ "pack_dtype": "int32",
38
+ "quant_method": "gptq",
39
+ "sym": true
40
+ },
41
+ "rms_norm_eps": 1e-06,
42
+ "rope_scaling": null,
43
+ "rope_theta": 1000000,
44
+ "sliding_window": null,
45
+ "tie_word_embeddings": false,
46
+ "torch_dtype": "bfloat16",
47
+ "transformers_version": "4.52.4",
48
+ "unsloth_fixed": true,
49
+ "unsloth_version": "2025.6.1",
50
+ "use_cache": true,
51
+ "use_sliding_window": false,
52
+ "vocab_size": 151936
53
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "max_length": 40960,
9
+ "pad_token_id": 151654,
10
+ "temperature": 0.6,
11
+ "top_k": 20,
12
+ "top_p": 0.95,
13
+ "transformers_version": "4.52.4"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e667d235dd1d0c5e88d7233fa5c9050ce5b6f84d716d3fdea9e9834b56f81e
3
+ size 3977460544
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f0f56ea784c85909a611619f7f187c5d2795869d89ade28ed1aa1f407a797f
3
+ size 2126456480
model.safetensors.index.json ADDED
@@ -0,0 +1,1162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6103787520
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
20
+ "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
21
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
24
+ "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
25
+ "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
26
+ "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
27
+ "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
28
+ "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
29
+ "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
30
+ "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
31
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
33
+ "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
34
+ "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
35
+ "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
36
+ "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
37
+ "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
38
+ "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
39
+ "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
40
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
42
+ "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
43
+ "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
44
+ "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
45
+ "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
46
+ "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
47
+ "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
48
+ "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
49
+ "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
50
+ "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
51
+ "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
52
+ "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
53
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
56
+ "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
57
+ "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
58
+ "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
59
+ "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
60
+ "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
61
+ "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
62
+ "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
63
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
65
+ "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
66
+ "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
67
+ "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
68
+ "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
69
+ "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
70
+ "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
71
+ "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
72
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
74
+ "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
75
+ "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
76
+ "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
77
+ "model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
78
+ "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
79
+ "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
80
+ "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
81
+ "model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
82
+ "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
83
+ "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
84
+ "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
85
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
88
+ "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
89
+ "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
90
+ "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
91
+ "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
92
+ "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
93
+ "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
94
+ "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
95
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
97
+ "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
98
+ "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
99
+ "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
100
+ "model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
101
+ "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
102
+ "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
103
+ "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
104
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
106
+ "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
107
+ "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
108
+ "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
109
+ "model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
110
+ "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
111
+ "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
112
+ "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
113
+ "model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
114
+ "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
115
+ "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
116
+ "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
117
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
120
+ "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
121
+ "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
122
+ "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
123
+ "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
124
+ "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
125
+ "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
126
+ "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
127
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
129
+ "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
130
+ "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
131
+ "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
132
+ "model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
133
+ "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
134
+ "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
135
+ "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
136
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
138
+ "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
139
+ "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
140
+ "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
141
+ "model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
142
+ "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
143
+ "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
144
+ "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
145
+ "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
146
+ "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
147
+ "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
148
+ "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
149
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
152
+ "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
153
+ "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
154
+ "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
155
+ "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
156
+ "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
157
+ "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
158
+ "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
159
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
161
+ "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
162
+ "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
163
+ "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
164
+ "model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
165
+ "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
166
+ "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
167
+ "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
168
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
170
+ "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
171
+ "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
172
+ "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
173
+ "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
174
+ "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
175
+ "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
176
+ "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
177
+ "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
178
+ "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
179
+ "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
180
+ "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
181
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
184
+ "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
185
+ "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
186
+ "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
187
+ "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
188
+ "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
189
+ "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
190
+ "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
191
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
193
+ "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
194
+ "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
195
+ "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
196
+ "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
197
+ "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
198
+ "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
199
+ "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
200
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
202
+ "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
203
+ "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
204
+ "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
205
+ "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
206
+ "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
207
+ "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
208
+ "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
209
+ "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
210
+ "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
211
+ "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
212
+ "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
213
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
216
+ "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
217
+ "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
218
+ "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
219
+ "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
220
+ "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
221
+ "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
222
+ "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
223
+ "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
225
+ "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
226
+ "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
227
+ "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
228
+ "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
229
+ "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
230
+ "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
231
+ "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
232
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
234
+ "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
235
+ "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
236
+ "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
237
+ "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
238
+ "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
239
+ "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
240
+ "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
241
+ "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
242
+ "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
243
+ "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
244
+ "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
245
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
248
+ "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
249
+ "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
250
+ "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
251
+ "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
252
+ "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
253
+ "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
254
+ "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
255
+ "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
257
+ "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
258
+ "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
259
+ "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
260
+ "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
261
+ "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
262
+ "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
263
+ "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
264
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
266
+ "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
267
+ "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
268
+ "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
269
+ "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
270
+ "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
271
+ "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
272
+ "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
273
+ "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
274
+ "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
275
+ "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
276
+ "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
277
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
280
+ "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
281
+ "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
282
+ "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
283
+ "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
284
+ "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
285
+ "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
286
+ "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
287
+ "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
289
+ "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
290
+ "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
291
+ "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
292
+ "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
293
+ "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
294
+ "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
295
+ "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
296
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
297
+ "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
298
+ "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
299
+ "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
300
+ "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
301
+ "model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
302
+ "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
303
+ "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
304
+ "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
305
+ "model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
306
+ "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
307
+ "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
308
+ "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
309
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
310
+ "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
311
+ "model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
312
+ "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
313
+ "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
314
+ "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
315
+ "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
316
+ "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
317
+ "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
318
+ "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
319
+ "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
320
+ "model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
321
+ "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
322
+ "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
323
+ "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
324
+ "model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
325
+ "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
326
+ "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
327
+ "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
328
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
329
+ "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
330
+ "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
331
+ "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
332
+ "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
333
+ "model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
334
+ "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
335
+ "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
336
+ "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
337
+ "model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
338
+ "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
339
+ "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
340
+ "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
341
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
343
+ "model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
344
+ "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
345
+ "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
346
+ "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
347
+ "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
348
+ "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
349
+ "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
350
+ "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
351
+ "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
352
+ "model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
353
+ "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
354
+ "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
355
+ "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
356
+ "model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
357
+ "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
358
+ "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
359
+ "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
360
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
362
+ "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
363
+ "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
364
+ "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
365
+ "model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
366
+ "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
367
+ "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
368
+ "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
369
+ "model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
370
+ "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
371
+ "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
372
+ "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
373
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
376
+ "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
377
+ "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
378
+ "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
379
+ "model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
380
+ "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
381
+ "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
382
+ "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
383
+ "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
385
+ "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
386
+ "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
387
+ "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
388
+ "model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
389
+ "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
390
+ "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
391
+ "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
392
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
394
+ "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
395
+ "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
396
+ "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
397
+ "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
398
+ "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
399
+ "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
400
+ "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
401
+ "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
402
+ "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
403
+ "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
404
+ "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
405
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
408
+ "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
409
+ "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
410
+ "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
411
+ "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
412
+ "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
413
+ "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
414
+ "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
415
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
417
+ "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
418
+ "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
419
+ "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
420
+ "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
421
+ "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
422
+ "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
423
+ "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
424
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
426
+ "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
427
+ "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
428
+ "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
429
+ "model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
430
+ "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
431
+ "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
432
+ "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
433
+ "model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
434
+ "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
435
+ "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
436
+ "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
437
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
439
+ "model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
440
+ "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
441
+ "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
442
+ "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
443
+ "model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
444
+ "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
445
+ "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
446
+ "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
447
+ "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
448
+ "model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
449
+ "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
450
+ "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
451
+ "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
452
+ "model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
453
+ "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
454
+ "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
455
+ "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
456
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
457
+ "model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
458
+ "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
459
+ "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
460
+ "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
461
+ "model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
462
+ "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
463
+ "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
464
+ "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
465
+ "model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
466
+ "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
467
+ "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
468
+ "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
469
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
470
+ "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
471
+ "model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
472
+ "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
473
+ "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
474
+ "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
475
+ "model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
476
+ "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
477
+ "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
478
+ "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
479
+ "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
480
+ "model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
481
+ "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
482
+ "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
483
+ "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
484
+ "model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
485
+ "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
486
+ "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
487
+ "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
488
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
489
+ "model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
490
+ "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
491
+ "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
492
+ "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
493
+ "model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
494
+ "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
495
+ "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
496
+ "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
497
+ "model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
498
+ "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
499
+ "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
500
+ "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
501
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
502
+ "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
503
+ "model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
504
+ "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
505
+ "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
506
+ "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
507
+ "model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
508
+ "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
509
+ "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
510
+ "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
511
+ "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
512
+ "model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
513
+ "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
514
+ "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
515
+ "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
516
+ "model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
517
+ "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
518
+ "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
519
+ "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
520
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
521
+ "model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
522
+ "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
523
+ "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
524
+ "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
525
+ "model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
526
+ "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
527
+ "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
528
+ "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
529
+ "model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
530
+ "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
531
+ "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
532
+ "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
533
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
534
+ "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
535
+ "model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
536
+ "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
537
+ "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
538
+ "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
539
+ "model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
540
+ "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
541
+ "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
542
+ "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
543
+ "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
544
+ "model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
545
+ "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
546
+ "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
547
+ "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
548
+ "model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
549
+ "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
550
+ "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
551
+ "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
552
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
553
+ "model.layers.24.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
554
+ "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
555
+ "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
556
+ "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
557
+ "model.layers.24.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
558
+ "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
559
+ "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
560
+ "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
561
+ "model.layers.24.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
562
+ "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
563
+ "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
564
+ "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
565
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
566
+ "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
567
+ "model.layers.24.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
568
+ "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
569
+ "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
570
+ "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
571
+ "model.layers.24.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
572
+ "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
573
+ "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
574
+ "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
575
+ "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
576
+ "model.layers.24.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
577
+ "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
578
+ "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
579
+ "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
580
+ "model.layers.24.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
581
+ "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
582
+ "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
583
+ "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
584
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
585
+ "model.layers.25.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
586
+ "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
587
+ "model.layers.25.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
588
+ "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
589
+ "model.layers.25.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
590
+ "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
591
+ "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
592
+ "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
593
+ "model.layers.25.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
594
+ "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
595
+ "model.layers.25.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
596
+ "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
597
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
598
+ "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
599
+ "model.layers.25.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
600
+ "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
601
+ "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
602
+ "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
603
+ "model.layers.25.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
604
+ "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
605
+ "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
606
+ "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
607
+ "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
608
+ "model.layers.25.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
609
+ "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
610
+ "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
611
+ "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
612
+ "model.layers.25.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
613
+ "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
614
+ "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
615
+ "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
616
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
617
+ "model.layers.26.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
618
+ "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
619
+ "model.layers.26.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
620
+ "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
621
+ "model.layers.26.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
622
+ "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
623
+ "model.layers.26.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
624
+ "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
625
+ "model.layers.26.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
626
+ "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
627
+ "model.layers.26.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
628
+ "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
629
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
630
+ "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
631
+ "model.layers.26.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
632
+ "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
633
+ "model.layers.26.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
634
+ "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
635
+ "model.layers.26.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
636
+ "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
637
+ "model.layers.26.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
638
+ "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
639
+ "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
640
+ "model.layers.26.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
641
+ "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
642
+ "model.layers.26.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
643
+ "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
644
+ "model.layers.26.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
645
+ "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
646
+ "model.layers.26.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
647
+ "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
648
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
649
+ "model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
650
+ "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
651
+ "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
652
+ "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
653
+ "model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
654
+ "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
655
+ "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
656
+ "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
657
+ "model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
658
+ "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
659
+ "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
660
+ "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
661
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
662
+ "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
663
+ "model.layers.27.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
664
+ "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
665
+ "model.layers.27.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
666
+ "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
667
+ "model.layers.27.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
668
+ "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
669
+ "model.layers.27.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
670
+ "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
671
+ "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
672
+ "model.layers.27.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
673
+ "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
674
+ "model.layers.27.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
675
+ "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
676
+ "model.layers.27.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
677
+ "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
678
+ "model.layers.27.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
679
+ "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
680
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
681
+ "model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
682
+ "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
683
+ "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
684
+ "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
685
+ "model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
686
+ "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
687
+ "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
688
+ "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
689
+ "model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
690
+ "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
691
+ "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
692
+ "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
693
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
694
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
695
+ "model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
696
+ "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
697
+ "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
698
+ "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
699
+ "model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
700
+ "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
701
+ "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
702
+ "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
703
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
704
+ "model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
705
+ "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
706
+ "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
707
+ "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
708
+ "model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
709
+ "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
710
+ "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
711
+ "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
712
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
713
+ "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
714
+ "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
715
+ "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
716
+ "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
717
+ "model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
718
+ "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
719
+ "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
720
+ "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
721
+ "model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
722
+ "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
723
+ "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
724
+ "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
725
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
726
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
727
+ "model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
728
+ "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
729
+ "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
730
+ "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
731
+ "model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
732
+ "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
733
+ "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
734
+ "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
735
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
736
+ "model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
737
+ "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
738
+ "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
739
+ "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
740
+ "model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
741
+ "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
742
+ "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
743
+ "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
744
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
745
+ "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
746
+ "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
747
+ "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
748
+ "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
749
+ "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
750
+ "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
751
+ "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
752
+ "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
753
+ "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
754
+ "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
755
+ "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
756
+ "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
757
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
758
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
759
+ "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
760
+ "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
761
+ "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
762
+ "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
763
+ "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
764
+ "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
765
+ "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
766
+ "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
767
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
768
+ "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
769
+ "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
770
+ "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
771
+ "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
772
+ "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
773
+ "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
774
+ "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
775
+ "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
776
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
777
+ "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
778
+ "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
779
+ "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
780
+ "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
781
+ "model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
782
+ "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
783
+ "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
784
+ "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
785
+ "model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
786
+ "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
787
+ "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
788
+ "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
789
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
790
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
791
+ "model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
792
+ "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
793
+ "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
794
+ "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
795
+ "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
796
+ "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
797
+ "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
798
+ "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
799
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
800
+ "model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
801
+ "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
802
+ "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
803
+ "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
804
+ "model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
805
+ "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
806
+ "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
807
+ "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
808
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
809
+ "model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
810
+ "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
811
+ "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
812
+ "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
813
+ "model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
814
+ "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
815
+ "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
816
+ "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
817
+ "model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
818
+ "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
819
+ "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
820
+ "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
821
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
822
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
823
+ "model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
824
+ "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
825
+ "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
826
+ "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
827
+ "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
828
+ "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
829
+ "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
830
+ "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
831
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
832
+ "model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
833
+ "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
834
+ "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
835
+ "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
836
+ "model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
837
+ "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
838
+ "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
839
+ "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
840
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
841
+ "model.layers.32.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
842
+ "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
843
+ "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
844
+ "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
845
+ "model.layers.32.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
846
+ "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
847
+ "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
848
+ "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
849
+ "model.layers.32.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
850
+ "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
851
+ "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
852
+ "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
853
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
854
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
855
+ "model.layers.32.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
856
+ "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
857
+ "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
858
+ "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
859
+ "model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
860
+ "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
861
+ "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
862
+ "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
863
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
864
+ "model.layers.32.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
865
+ "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
866
+ "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
867
+ "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
868
+ "model.layers.32.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
869
+ "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
870
+ "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
871
+ "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
872
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
873
+ "model.layers.33.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
874
+ "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
875
+ "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
876
+ "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
877
+ "model.layers.33.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
878
+ "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
879
+ "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
880
+ "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
881
+ "model.layers.33.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
882
+ "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
883
+ "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
884
+ "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
885
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
886
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
887
+ "model.layers.33.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
888
+ "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
889
+ "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
890
+ "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
891
+ "model.layers.33.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
892
+ "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
893
+ "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
894
+ "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
895
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
896
+ "model.layers.33.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
897
+ "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
898
+ "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
899
+ "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
900
+ "model.layers.33.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
901
+ "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
902
+ "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
903
+ "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
904
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
905
+ "model.layers.34.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
906
+ "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
907
+ "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
908
+ "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
909
+ "model.layers.34.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
910
+ "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
911
+ "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
912
+ "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
913
+ "model.layers.34.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
914
+ "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
915
+ "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
916
+ "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
917
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
918
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
919
+ "model.layers.34.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
920
+ "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
921
+ "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
922
+ "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
923
+ "model.layers.34.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
924
+ "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
925
+ "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
926
+ "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
927
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
928
+ "model.layers.34.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
929
+ "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
930
+ "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
931
+ "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
932
+ "model.layers.34.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
933
+ "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
934
+ "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
935
+ "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
936
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
937
+ "model.layers.35.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
938
+ "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
939
+ "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
940
+ "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
941
+ "model.layers.35.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
942
+ "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
943
+ "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
944
+ "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
945
+ "model.layers.35.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
946
+ "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
947
+ "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
948
+ "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
949
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
950
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
951
+ "model.layers.35.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
952
+ "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
953
+ "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
954
+ "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
955
+ "model.layers.35.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
956
+ "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
957
+ "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
958
+ "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
959
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
960
+ "model.layers.35.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
961
+ "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
962
+ "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
963
+ "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
964
+ "model.layers.35.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
965
+ "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
966
+ "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
967
+ "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
968
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
969
+ "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
970
+ "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
971
+ "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
972
+ "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
973
+ "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
974
+ "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
975
+ "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
976
+ "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
977
+ "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
978
+ "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
979
+ "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
980
+ "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
981
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
982
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
983
+ "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
984
+ "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
985
+ "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
986
+ "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
987
+ "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
988
+ "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
989
+ "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
990
+ "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
991
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
992
+ "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
993
+ "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
994
+ "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
995
+ "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
996
+ "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
997
+ "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
998
+ "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
999
+ "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1000
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
1001
+ "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
1002
+ "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1003
+ "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1004
+ "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1005
+ "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
1006
+ "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1007
+ "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1008
+ "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1009
+ "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
1010
+ "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1011
+ "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1012
+ "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1013
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1014
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
1015
+ "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
1016
+ "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1017
+ "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1018
+ "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1019
+ "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
1020
+ "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1021
+ "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1022
+ "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1023
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
1024
+ "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
1025
+ "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1026
+ "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1027
+ "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1028
+ "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
1029
+ "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1030
+ "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1031
+ "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1032
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
1033
+ "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
1034
+ "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1035
+ "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1036
+ "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1037
+ "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
1038
+ "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1039
+ "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1040
+ "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1041
+ "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
1042
+ "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1043
+ "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1044
+ "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1045
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1046
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
1047
+ "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
1048
+ "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1049
+ "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1050
+ "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1051
+ "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
1052
+ "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1053
+ "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1054
+ "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1055
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
1056
+ "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
1057
+ "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1058
+ "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1059
+ "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1060
+ "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
1061
+ "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1062
+ "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1063
+ "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1064
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
1065
+ "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
1066
+ "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1067
+ "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1068
+ "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1069
+ "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
1070
+ "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1071
+ "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1072
+ "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1073
+ "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
1074
+ "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1075
+ "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1076
+ "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1077
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1078
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
1079
+ "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
1080
+ "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1081
+ "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1082
+ "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1083
+ "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
1084
+ "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1085
+ "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1086
+ "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1087
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
1088
+ "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
1089
+ "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1090
+ "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1091
+ "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1092
+ "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
1093
+ "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1094
+ "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1095
+ "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1096
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
1097
+ "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
1098
+ "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1099
+ "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1100
+ "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1101
+ "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
1102
+ "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1103
+ "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1104
+ "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1105
+ "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
1106
+ "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1107
+ "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1108
+ "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1109
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1110
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
1111
+ "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
1112
+ "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1113
+ "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1114
+ "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1115
+ "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
1116
+ "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1117
+ "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1118
+ "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1119
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
1120
+ "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
1121
+ "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1122
+ "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1123
+ "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1124
+ "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
1125
+ "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1126
+ "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1127
+ "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1128
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
1129
+ "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
1130
+ "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
1131
+ "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
1132
+ "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1133
+ "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
1134
+ "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
1135
+ "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
1136
+ "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1137
+ "model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
1138
+ "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
1139
+ "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
1140
+ "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1141
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1142
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
1143
+ "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
1144
+ "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
1145
+ "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
1146
+ "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1147
+ "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
1148
+ "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
1149
+ "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
1150
+ "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1151
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
1152
+ "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
1153
+ "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
1154
+ "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
1155
+ "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1156
+ "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
1157
+ "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
1158
+ "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
1159
+ "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1160
+ "model.norm.weight": "model-00002-of-00002.safetensors"
1161
+ }
1162
+ }
quant_log.csv ADDED
@@ -0,0 +1,253 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ layer,module,loss,samples,damp,time
2
+ 0,self_attn.k_proj,0.00081898,0.01000,0.930
3
+ 0,self_attn.v_proj,0.00066658,0.01000,0.910
4
+ 0,self_attn.q_proj,0.00266221,0.01000,0.955
5
+ 0,self_attn.o_proj,0.01056377,0.01000,0.981
6
+ 0,mlp.up_proj,0.36460605,0.01000,1.014
7
+ 0,mlp.gate_proj,0.41476089,0.01000,0.990
8
+ 0,mlp.down_proj,0.11316967,0.01000,3.332
9
+ 1,self_attn.k_proj,0.00274886,0.01000,0.983
10
+ 1,self_attn.v_proj,0.00292343,0.01000,0.963
11
+ 1,self_attn.q_proj,0.00942496,0.01000,0.970
12
+ 1,self_attn.o_proj,0.01591702,0.01000,0.990
13
+ 1,mlp.up_proj,3.48117876,0.01000,1.019
14
+ 1,mlp.gate_proj,8.76610851,0.01000,0.997
15
+ 1,mlp.down_proj,0.10971618,0.01000,3.338
16
+ 2,self_attn.k_proj,0.00680250,0.01000,0.953
17
+ 2,self_attn.v_proj,0.00658121,0.01000,0.938
18
+ 2,self_attn.q_proj,0.02308291,0.01000,0.972
19
+ 2,self_attn.o_proj,0.01615234,0.01000,0.989
20
+ 2,mlp.up_proj,12.98209000,0.01000,1.028
21
+ 2,mlp.gate_proj,16.81762123,0.01000,0.972
22
+ 2,mlp.down_proj,0.08382411,0.01000,3.338
23
+ 3,self_attn.k_proj,0.01154783,0.01000,0.955
24
+ 3,self_attn.v_proj,0.01182674,0.01000,0.921
25
+ 3,self_attn.q_proj,0.04141535,0.01000,0.972
26
+ 3,self_attn.o_proj,0.02680396,0.01000,0.982
27
+ 3,mlp.up_proj,7.65060997,0.01000,1.027
28
+ 3,mlp.gate_proj,16.55635071,0.01000,0.996
29
+ 3,mlp.down_proj,0.23596868,0.01000,3.342
30
+ 4,self_attn.k_proj,0.02555137,0.01000,0.994
31
+ 4,self_attn.v_proj,0.02623437,0.01000,0.963
32
+ 4,self_attn.q_proj,0.08924785,0.01000,0.966
33
+ 4,self_attn.o_proj,0.04677752,0.01000,0.992
34
+ 4,mlp.up_proj,7.30070257,0.01000,1.029
35
+ 4,mlp.gate_proj,19.08970261,0.01000,0.998
36
+ 4,mlp.down_proj,0.47609770,0.01000,3.326
37
+ 5,self_attn.k_proj,0.02471795,0.01000,0.997
38
+ 5,self_attn.v_proj,0.02619038,0.01000,0.963
39
+ 5,self_attn.q_proj,0.09057556,0.01000,0.968
40
+ 5,self_attn.o_proj,0.06916548,0.01000,0.990
41
+ 5,mlp.up_proj,4.68818855,0.01000,1.018
42
+ 5,mlp.gate_proj,10.25698757,0.01000,0.991
43
+ 5,mlp.down_proj,0.69139361,0.01000,3.426
44
+ 6,self_attn.k_proj,0.04606379,0.01000,0.992
45
+ 6,self_attn.v_proj,0.05108695,0.01000,0.963
46
+ 6,self_attn.q_proj,0.18342555,0.01000,0.970
47
+ 6,self_attn.o_proj,0.19215500,0.01000,0.983
48
+ 6,mlp.up_proj,6.43126774,0.01000,1.020
49
+ 6,mlp.gate_proj,12.42700386,0.01000,0.995
50
+ 6,mlp.down_proj,39.82849121,0.01000,3.355
51
+ 7,self_attn.k_proj,0.11290302,0.01000,0.995
52
+ 7,self_attn.v_proj,0.11030604,0.01000,0.963
53
+ 7,self_attn.q_proj,0.39779568,0.01000,0.976
54
+ 7,self_attn.o_proj,0.16358313,0.01000,0.997
55
+ 7,mlp.up_proj,7.58053160,0.01000,1.033
56
+ 7,mlp.gate_proj,13.41549873,0.01000,1.017
57
+ 7,mlp.down_proj,0.94745064,0.01000,3.367
58
+ 8,self_attn.k_proj,0.17907880,0.01000,1.000
59
+ 8,self_attn.v_proj,0.18876882,0.01000,0.969
60
+ 8,self_attn.q_proj,0.64190459,0.01000,0.970
61
+ 8,self_attn.o_proj,0.28301448,0.01000,0.996
62
+ 8,mlp.up_proj,7.10559034,0.01000,1.029
63
+ 8,mlp.gate_proj,8.11741829,0.01000,0.997
64
+ 8,mlp.down_proj,1.72153497,0.01000,3.357
65
+ 9,self_attn.k_proj,0.24353266,0.01000,0.996
66
+ 9,self_attn.v_proj,0.22538465,0.01000,0.965
67
+ 9,self_attn.q_proj,0.84267175,0.01000,0.971
68
+ 9,self_attn.o_proj,0.37646514,0.01000,0.995
69
+ 9,mlp.up_proj,9.17837620,0.01000,1.025
70
+ 9,mlp.gate_proj,12.42196846,0.01000,0.996
71
+ 9,mlp.down_proj,1.98623919,0.01000,3.344
72
+ 10,self_attn.k_proj,0.44182873,0.01000,0.998
73
+ 10,self_attn.v_proj,0.49409217,0.01000,0.971
74
+ 10,self_attn.q_proj,1.59092176,0.01000,0.975
75
+ 10,self_attn.o_proj,0.48631072,0.01000,0.994
76
+ 10,mlp.up_proj,9.16933823,0.01000,1.030
77
+ 10,mlp.gate_proj,11.79351807,0.01000,1.000
78
+ 10,mlp.down_proj,2.10669732,0.01000,3.378
79
+ 11,self_attn.k_proj,0.23384133,0.01000,1.000
80
+ 11,self_attn.v_proj,0.23612824,0.01000,0.966
81
+ 11,self_attn.q_proj,0.81552625,0.01000,0.974
82
+ 11,self_attn.o_proj,0.46933773,0.01000,0.997
83
+ 11,mlp.up_proj,9.38166714,0.01000,1.043
84
+ 11,mlp.gate_proj,11.07245445,0.01000,1.015
85
+ 11,mlp.down_proj,2.13181925,0.01000,3.428
86
+ 12,self_attn.k_proj,0.27170113,0.01000,0.988
87
+ 12,self_attn.v_proj,0.28498989,0.01000,0.962
88
+ 12,self_attn.q_proj,0.95448577,0.01000,0.972
89
+ 12,self_attn.o_proj,0.57324892,0.01000,0.963
90
+ 12,mlp.up_proj,10.03530407,0.01000,1.037
91
+ 12,mlp.gate_proj,11.01393509,0.01000,1.001
92
+ 12,mlp.down_proj,2.29487896,0.01000,3.388
93
+ 13,self_attn.k_proj,0.22276369,0.01000,0.993
94
+ 13,self_attn.v_proj,0.21455717,0.01000,0.971
95
+ 13,self_attn.q_proj,0.81629038,0.01000,0.976
96
+ 13,self_attn.o_proj,0.42701221,0.01000,1.000
97
+ 13,mlp.up_proj,10.49976158,0.01000,1.033
98
+ 13,mlp.gate_proj,10.70145893,0.01000,1.002
99
+ 13,mlp.down_proj,2.60380840,0.01000,3.357
100
+ 14,self_attn.k_proj,0.37535098,0.01000,1.004
101
+ 14,self_attn.v_proj,0.39157313,0.01000,0.973
102
+ 14,self_attn.q_proj,1.37911272,0.01000,0.979
103
+ 14,self_attn.o_proj,0.80457497,0.01000,0.993
104
+ 14,mlp.up_proj,10.72129440,0.01000,1.022
105
+ 14,mlp.gate_proj,10.83584213,0.01000,1.007
106
+ 14,mlp.down_proj,2.57154799,0.01000,3.362
107
+ 15,self_attn.k_proj,0.39861578,0.01000,0.959
108
+ 15,self_attn.v_proj,0.38187337,0.01000,0.956
109
+ 15,self_attn.q_proj,1.42467535,0.01000,0.985
110
+ 15,self_attn.o_proj,0.62761331,0.01000,0.956
111
+ 15,mlp.up_proj,10.44326878,0.01000,0.966
112
+ 15,mlp.gate_proj,10.13860321,0.01000,0.934
113
+ 15,mlp.down_proj,2.66034722,0.01000,3.164
114
+ 16,self_attn.k_proj,0.69915050,0.01000,0.931
115
+ 16,self_attn.v_proj,0.79679632,0.01000,0.898
116
+ 16,self_attn.q_proj,2.69724488,0.01000,0.902
117
+ 16,self_attn.o_proj,0.90162665,0.01000,0.925
118
+ 16,mlp.up_proj,12.03856277,0.01000,0.963
119
+ 16,mlp.gate_proj,12.08769608,0.01000,0.932
120
+ 16,mlp.down_proj,7.32658958,0.01000,3.143
121
+ 17,self_attn.k_proj,0.69720548,0.01000,0.909
122
+ 17,self_attn.v_proj,0.77622926,0.01000,0.877
123
+ 17,self_attn.q_proj,2.85146189,0.01000,0.882
124
+ 17,self_attn.o_proj,1.11090648,0.01000,0.905
125
+ 17,mlp.up_proj,11.91839600,0.01000,0.938
126
+ 17,mlp.gate_proj,11.61888885,0.01000,0.911
127
+ 17,mlp.down_proj,4.19483757,0.01000,3.096
128
+ 18,self_attn.k_proj,0.81944716,0.01000,0.958
129
+ 18,self_attn.v_proj,0.88214433,0.01000,0.878
130
+ 18,self_attn.q_proj,3.12404394,0.01000,0.916
131
+ 18,self_attn.o_proj,1.20161247,0.01000,0.925
132
+ 18,mlp.up_proj,13.55004978,0.01000,0.960
133
+ 18,mlp.gate_proj,13.19692612,0.01000,0.932
134
+ 18,mlp.down_proj,4.46299171,0.01000,3.153
135
+ 19,self_attn.k_proj,1.61722660,0.01000,0.931
136
+ 19,self_attn.v_proj,1.69101739,0.01000,0.909
137
+ 19,self_attn.q_proj,6.37774277,0.01000,0.912
138
+ 19,self_attn.o_proj,1.97588265,0.01000,0.927
139
+ 19,mlp.up_proj,15.75208664,0.01000,0.962
140
+ 19,mlp.gate_proj,15.12816429,0.01000,0.932
141
+ 19,mlp.down_proj,5.88752890,0.01000,3.154
142
+ 20,self_attn.k_proj,1.40967464,0.01000,0.930
143
+ 20,self_attn.v_proj,1.60080421,0.01000,0.898
144
+ 20,self_attn.q_proj,6.02798176,0.01000,0.902
145
+ 20,self_attn.o_proj,1.99192619,0.01000,0.926
146
+ 20,mlp.up_proj,17.76055527,0.01000,0.962
147
+ 20,mlp.gate_proj,16.75141525,0.01000,0.932
148
+ 20,mlp.down_proj,7.02390528,0.01000,3.151
149
+ 21,self_attn.k_proj,1.93168008,0.01000,0.928
150
+ 21,self_attn.v_proj,2.32839441,0.01000,0.899
151
+ 21,self_attn.q_proj,7.93037605,0.01000,0.903
152
+ 21,self_attn.o_proj,2.33001137,0.01000,0.923
153
+ 21,mlp.up_proj,20.97650146,0.01000,0.959
154
+ 21,mlp.gate_proj,19.60754967,0.01000,0.932
155
+ 21,mlp.down_proj,9.47710514,0.01000,3.150
156
+ 22,self_attn.k_proj,4.38026810,0.01000,0.951
157
+ 22,self_attn.v_proj,4.76986408,0.01000,0.881
158
+ 22,self_attn.q_proj,17.14842033,0.01000,0.885
159
+ 22,self_attn.o_proj,4.70186186,0.01000,0.908
160
+ 22,mlp.up_proj,24.83567047,0.01000,0.944
161
+ 22,mlp.gate_proj,23.42943954,0.01000,0.914
162
+ 22,mlp.down_proj,15.90500259,0.01000,3.099
163
+ 23,self_attn.k_proj,4.39575863,0.01000,0.912
164
+ 23,self_attn.v_proj,5.49318504,0.01000,0.879
165
+ 23,self_attn.q_proj,18.27279663,0.01000,0.886
166
+ 23,self_attn.o_proj,7.11719418,0.01000,0.908
167
+ 23,mlp.up_proj,28.74668694,0.01000,0.947
168
+ 23,mlp.gate_proj,27.82252884,0.01000,0.915
169
+ 23,mlp.down_proj,22.27873039,0.01000,3.150
170
+ 24,self_attn.k_proj,7.76150322,0.01000,0.911
171
+ 24,self_attn.v_proj,10.02000999,0.01000,0.880
172
+ 24,self_attn.q_proj,32.13746643,0.01000,0.885
173
+ 24,self_attn.o_proj,8.39258480,0.01000,0.908
174
+ 24,mlp.up_proj,31.80643082,0.01000,0.947
175
+ 24,mlp.gate_proj,31.17360878,0.01000,0.917
176
+ 24,mlp.down_proj,26.38691711,0.01000,3.207
177
+ 25,self_attn.k_proj,6.23285007,0.01000,0.956
178
+ 25,self_attn.v_proj,7.53075695,0.01000,0.884
179
+ 25,self_attn.q_proj,24.82022476,0.01000,0.895
180
+ 25,self_attn.o_proj,5.23707581,0.01000,0.948
181
+ 25,mlp.up_proj,36.12810898,0.01000,0.973
182
+ 25,mlp.gate_proj,35.83207321,0.01000,0.939
183
+ 25,mlp.down_proj,32.88881683,0.01000,3.173
184
+ 26,self_attn.k_proj,10.20067215,0.01000,0.936
185
+ 26,self_attn.v_proj,12.58343697,0.01000,0.903
186
+ 26,self_attn.q_proj,41.61561584,0.01000,0.932
187
+ 26,self_attn.o_proj,6.34464645,0.01000,0.933
188
+ 26,mlp.up_proj,43.97548676,0.01000,0.969
189
+ 26,mlp.gate_proj,42.95751572,0.01000,0.939
190
+ 26,mlp.down_proj,38.91927719,0.01000,3.176
191
+ 27,self_attn.k_proj,11.28719807,0.01000,0.936
192
+ 27,self_attn.v_proj,15.30759811,0.01000,0.918
193
+ 27,self_attn.q_proj,47.44653320,0.01000,0.910
194
+ 27,self_attn.o_proj,6.93713140,0.01000,0.932
195
+ 27,mlp.up_proj,49.93562317,0.01000,0.968
196
+ 27,mlp.gate_proj,47.99846268,0.01000,0.938
197
+ 27,mlp.down_proj,53.05934906,0.01000,3.173
198
+ 28,self_attn.k_proj,13.16033936,0.01000,0.935
199
+ 28,self_attn.v_proj,15.21002960,0.01000,0.901
200
+ 28,self_attn.q_proj,50.68807602,0.01000,0.907
201
+ 28,self_attn.o_proj,11.12988663,0.01000,0.932
202
+ 28,mlp.up_proj,58.48759842,0.01000,0.968
203
+ 28,mlp.gate_proj,54.71423340,0.01000,0.938
204
+ 28,mlp.down_proj,73.80397034,0.01000,3.180
205
+ 29,self_attn.k_proj,29.57807922,0.01000,0.935
206
+ 29,self_attn.v_proj,43.38948059,0.01000,0.903
207
+ 29,self_attn.q_proj,115.62554932,0.01000,0.910
208
+ 29,self_attn.o_proj,12.59876823,0.01000,0.933
209
+ 29,mlp.up_proj,68.68040466,0.01000,0.969
210
+ 29,mlp.gate_proj,62.38510513,0.01000,0.937
211
+ 29,mlp.down_proj,80.62075806,0.01000,3.173
212
+ 30,self_attn.k_proj,35.26361084,0.01000,0.934
213
+ 30,self_attn.v_proj,46.33374023,0.01000,0.904
214
+ 30,self_attn.q_proj,132.53497314,0.01000,0.910
215
+ 30,self_attn.o_proj,17.81767082,0.01000,0.930
216
+ 30,mlp.up_proj,74.55784607,0.01000,0.970
217
+ 30,mlp.gate_proj,66.18569946,0.01000,0.938
218
+ 30,mlp.down_proj,106.52716064,0.01000,3.177
219
+ 31,self_attn.k_proj,49.98489380,0.01000,0.947
220
+ 31,self_attn.v_proj,69.49468231,0.01000,0.932
221
+ 31,self_attn.q_proj,170.69680786,0.01000,0.912
222
+ 31,self_attn.o_proj,21.39829254,0.01000,0.932
223
+ 31,mlp.up_proj,79.79562378,0.01000,0.969
224
+ 31,mlp.gate_proj,68.45579529,0.01000,0.941
225
+ 31,mlp.down_proj,135.01379395,0.01000,3.169
226
+ 32,self_attn.k_proj,67.02267456,0.01000,0.936
227
+ 32,self_attn.v_proj,101.60980225,0.01000,0.905
228
+ 32,self_attn.q_proj,252.53392029,0.01000,0.910
229
+ 32,self_attn.o_proj,30.39963531,0.01000,0.932
230
+ 32,mlp.up_proj,84.75903320,0.01000,0.967
231
+ 32,mlp.gate_proj,71.21557617,0.01000,0.951
232
+ 32,mlp.down_proj,173.03173828,0.01000,3.169
233
+ 33,self_attn.k_proj,117.32642365,0.01000,0.936
234
+ 33,self_attn.v_proj,222.11895752,0.01000,0.906
235
+ 33,self_attn.q_proj,504.20962524,0.01000,0.910
236
+ 33,self_attn.o_proj,55.01433563,0.01000,0.931
237
+ 33,mlp.up_proj,91.39668274,0.01000,0.968
238
+ 33,mlp.gate_proj,75.59240723,0.01000,0.939
239
+ 33,mlp.down_proj,222.78610229,0.01000,3.176
240
+ 34,self_attn.k_proj,96.66996765,0.01000,0.935
241
+ 34,self_attn.v_proj,151.39541626,0.01000,0.901
242
+ 34,self_attn.q_proj,409.25778198,0.01000,0.908
243
+ 34,self_attn.o_proj,78.65682983,0.01000,0.929
244
+ 34,mlp.up_proj,98.67007446,0.01000,0.968
245
+ 34,mlp.gate_proj,85.93466187,0.01000,0.937
246
+ 34,mlp.down_proj,313.34213257,0.01000,3.154
247
+ 35,self_attn.k_proj,47.45104218,0.01000,0.931
248
+ 35,self_attn.v_proj,62.73534393,0.01000,0.899
249
+ 35,self_attn.q_proj,178.08447266,0.01000,0.905
250
+ 35,self_attn.o_proj,59.25527191,0.01000,0.931
251
+ 35,mlp.up_proj,119.87613678,0.01000,0.963
252
+ 35,mlp.gate_proj,109.75646973,0.01000,0.932
253
+ 35,mlp.down_proj,1514.94860840,0.01000,3.159
quantize_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "desc_act": true,
5
+ "sym": true,
6
+ "lm_head": false,
7
+ "quant_method": "gptq",
8
+ "checkpoint_format": "gptq",
9
+ "pack_dtype": "int32",
10
+ "meta": {
11
+ "quantizer": [
12
+ "gptqmodel:2.2.0"
13
+ ],
14
+ "uri": "https://github.com/modelcloud/gptqmodel",
15
+ "damp_percent": 0.01,
16
+ "damp_auto_increment": 0.0025,
17
+ "static_groups": false,
18
+ "true_sequential": true,
19
+ "mse": 0.0
20
+ }
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": "<|vision_pad|>"
25
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 40960,
235
+ "pad_token": "<|vision_pad|>",
236
+ "padding_side": "right",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2TokenizerFast",
239
+ "unk_token": null,
240
+ "_commit_hash": null
241
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff