sionic commited on
Commit
cf6246f
·
verified ·
1 Parent(s): b1e7150

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 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: google/gemma-3-270m-it
3
+ license: gemma
4
+ tags:
5
+ - gemma3
6
+ - gemma
7
+ - google
8
+ - mlx
9
+ pipeline_tag: text-generation
10
+ library_name: mlx
11
+ extra_gated_heading: Access Gemma on Hugging Face
12
+ extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
13
+ agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging
14
+ Face and click below. Requests are processed immediately.
15
+ extra_gated_button_content: Acknowledge license
16
+ ---
17
+
18
+ # sionic-ai/mlx-gemma-3-270m-it
19
+
20
+ This model [sionic-ai/mlx-gemma-3-270m-it](https://huggingface.co/sionic-ai/mlx-gemma-3-270m-it) was
21
+ converted to MLX format from [google/gemma-3-270m-it](https://huggingface.co/google/gemma-3-270m-it)
22
+ using mlx-lm version **0.26.3**.
23
+
24
+ ## Use with mlx
25
+
26
+ ```bash
27
+ pip install mlx-lm
28
+ ```
29
+
30
+ ```python
31
+ from mlx_lm import load, generate
32
+
33
+ model, tokenizer = load("sionic-ai/mlx-gemma-3-270m-it")
34
+
35
+ prompt = "hello"
36
+
37
+ if tokenizer.chat_template is not None:
38
+ messages = [{"role": "user", "content": prompt}]
39
+ prompt = tokenizer.apply_chat_template(
40
+ messages, add_generation_prompt=True
41
+ )
42
+
43
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
44
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "eos_token_id": 1,
11
+ "final_logit_softcapping": null,
12
+ "head_dim": 256,
13
+ "hidden_activation": "gelu_pytorch_tanh",
14
+ "hidden_size": 640,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2048,
17
+ "layer_types": [
18
+ "sliding_attention",
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "full_attention",
30
+ "sliding_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "full_attention"
36
+ ],
37
+ "max_position_embeddings": 32768,
38
+ "model_type": "gemma3_text",
39
+ "num_attention_heads": 4,
40
+ "num_hidden_layers": 18,
41
+ "num_key_value_heads": 1,
42
+ "pad_token_id": 0,
43
+ "query_pre_attn_scalar": 256,
44
+ "rms_norm_eps": 1e-06,
45
+ "rope_local_base_freq": 10000.0,
46
+ "rope_scaling": null,
47
+ "rope_theta": 1000000.0,
48
+ "sliding_window": 512,
49
+ "torch_dtype": "bfloat16",
50
+ "transformers_version": "4.55.0.dev0",
51
+ "use_bidirectional_attention": false,
52
+ "use_cache": true,
53
+ "vocab_size": 262144
54
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cache_implementation": "hybrid",
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 1,
6
+ 106
7
+ ],
8
+ "top_k": 64,
9
+ "top_p": 0.95,
10
+ "transformers_version": "4.55.0.dev0"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1404199e25dfbb61f50a99382cf70dff5bfc4529f2ad350d1bf278bf4d4d34b0
3
+ size 871767180
model.safetensors.index.json ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 871740672,
4
+ "total_parameters": 435870336
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model.safetensors",
8
+ "model.embed_tokens.weight": "model.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
14
+ "model.layers.0.post_feedforward_layernorm.weight": "model.safetensors",
15
+ "model.layers.0.pre_feedforward_layernorm.weight": "model.safetensors",
16
+ "model.layers.0.self_attn.k_norm.weight": "model.safetensors",
17
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
18
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
19
+ "model.layers.0.self_attn.q_norm.weight": "model.safetensors",
20
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
21
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
22
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
23
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
24
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
25
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
26
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
27
+ "model.layers.1.post_feedforward_layernorm.weight": "model.safetensors",
28
+ "model.layers.1.pre_feedforward_layernorm.weight": "model.safetensors",
29
+ "model.layers.1.self_attn.k_norm.weight": "model.safetensors",
30
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
31
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
32
+ "model.layers.1.self_attn.q_norm.weight": "model.safetensors",
33
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
34
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
35
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
36
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
37
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
38
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
39
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
40
+ "model.layers.10.post_feedforward_layernorm.weight": "model.safetensors",
41
+ "model.layers.10.pre_feedforward_layernorm.weight": "model.safetensors",
42
+ "model.layers.10.self_attn.k_norm.weight": "model.safetensors",
43
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
44
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
45
+ "model.layers.10.self_attn.q_norm.weight": "model.safetensors",
46
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
47
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
48
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
49
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
50
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
51
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
52
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
53
+ "model.layers.11.post_feedforward_layernorm.weight": "model.safetensors",
54
+ "model.layers.11.pre_feedforward_layernorm.weight": "model.safetensors",
55
+ "model.layers.11.self_attn.k_norm.weight": "model.safetensors",
56
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
57
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
58
+ "model.layers.11.self_attn.q_norm.weight": "model.safetensors",
59
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
60
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
61
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
62
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
63
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
64
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
65
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
66
+ "model.layers.12.post_feedforward_layernorm.weight": "model.safetensors",
67
+ "model.layers.12.pre_feedforward_layernorm.weight": "model.safetensors",
68
+ "model.layers.12.self_attn.k_norm.weight": "model.safetensors",
69
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
70
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
71
+ "model.layers.12.self_attn.q_norm.weight": "model.safetensors",
72
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
73
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
74
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
75
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
76
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
77
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
78
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
79
+ "model.layers.13.post_feedforward_layernorm.weight": "model.safetensors",
80
+ "model.layers.13.pre_feedforward_layernorm.weight": "model.safetensors",
81
+ "model.layers.13.self_attn.k_norm.weight": "model.safetensors",
82
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
83
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
84
+ "model.layers.13.self_attn.q_norm.weight": "model.safetensors",
85
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
86
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
87
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
88
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
89
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
90
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
91
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
92
+ "model.layers.14.post_feedforward_layernorm.weight": "model.safetensors",
93
+ "model.layers.14.pre_feedforward_layernorm.weight": "model.safetensors",
94
+ "model.layers.14.self_attn.k_norm.weight": "model.safetensors",
95
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
96
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
97
+ "model.layers.14.self_attn.q_norm.weight": "model.safetensors",
98
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
99
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
100
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
101
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
102
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
103
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
104
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
105
+ "model.layers.15.post_feedforward_layernorm.weight": "model.safetensors",
106
+ "model.layers.15.pre_feedforward_layernorm.weight": "model.safetensors",
107
+ "model.layers.15.self_attn.k_norm.weight": "model.safetensors",
108
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
109
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
110
+ "model.layers.15.self_attn.q_norm.weight": "model.safetensors",
111
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
112
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
113
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
114
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
115
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
116
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
117
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
118
+ "model.layers.16.post_feedforward_layernorm.weight": "model.safetensors",
119
+ "model.layers.16.pre_feedforward_layernorm.weight": "model.safetensors",
120
+ "model.layers.16.self_attn.k_norm.weight": "model.safetensors",
121
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
122
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
123
+ "model.layers.16.self_attn.q_norm.weight": "model.safetensors",
124
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
125
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
126
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
127
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
128
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
129
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
130
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
131
+ "model.layers.17.post_feedforward_layernorm.weight": "model.safetensors",
132
+ "model.layers.17.pre_feedforward_layernorm.weight": "model.safetensors",
133
+ "model.layers.17.self_attn.k_norm.weight": "model.safetensors",
134
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
135
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
136
+ "model.layers.17.self_attn.q_norm.weight": "model.safetensors",
137
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
138
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
139
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
140
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
141
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
142
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
143
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
144
+ "model.layers.2.post_feedforward_layernorm.weight": "model.safetensors",
145
+ "model.layers.2.pre_feedforward_layernorm.weight": "model.safetensors",
146
+ "model.layers.2.self_attn.k_norm.weight": "model.safetensors",
147
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
148
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
149
+ "model.layers.2.self_attn.q_norm.weight": "model.safetensors",
150
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
151
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
152
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
153
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
154
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
155
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
156
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
157
+ "model.layers.3.post_feedforward_layernorm.weight": "model.safetensors",
158
+ "model.layers.3.pre_feedforward_layernorm.weight": "model.safetensors",
159
+ "model.layers.3.self_attn.k_norm.weight": "model.safetensors",
160
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
161
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
162
+ "model.layers.3.self_attn.q_norm.weight": "model.safetensors",
163
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
164
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
165
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
166
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
167
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
168
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
169
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
170
+ "model.layers.4.post_feedforward_layernorm.weight": "model.safetensors",
171
+ "model.layers.4.pre_feedforward_layernorm.weight": "model.safetensors",
172
+ "model.layers.4.self_attn.k_norm.weight": "model.safetensors",
173
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
174
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
175
+ "model.layers.4.self_attn.q_norm.weight": "model.safetensors",
176
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
177
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
178
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
179
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
180
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
181
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
182
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
183
+ "model.layers.5.post_feedforward_layernorm.weight": "model.safetensors",
184
+ "model.layers.5.pre_feedforward_layernorm.weight": "model.safetensors",
185
+ "model.layers.5.self_attn.k_norm.weight": "model.safetensors",
186
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
187
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
188
+ "model.layers.5.self_attn.q_norm.weight": "model.safetensors",
189
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
190
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
191
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
192
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
193
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
194
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
195
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
196
+ "model.layers.6.post_feedforward_layernorm.weight": "model.safetensors",
197
+ "model.layers.6.pre_feedforward_layernorm.weight": "model.safetensors",
198
+ "model.layers.6.self_attn.k_norm.weight": "model.safetensors",
199
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
200
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
201
+ "model.layers.6.self_attn.q_norm.weight": "model.safetensors",
202
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
203
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
204
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
205
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
206
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
207
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
208
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
209
+ "model.layers.7.post_feedforward_layernorm.weight": "model.safetensors",
210
+ "model.layers.7.pre_feedforward_layernorm.weight": "model.safetensors",
211
+ "model.layers.7.self_attn.k_norm.weight": "model.safetensors",
212
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
213
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
214
+ "model.layers.7.self_attn.q_norm.weight": "model.safetensors",
215
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
216
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
217
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
218
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
219
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
220
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
221
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
222
+ "model.layers.8.post_feedforward_layernorm.weight": "model.safetensors",
223
+ "model.layers.8.pre_feedforward_layernorm.weight": "model.safetensors",
224
+ "model.layers.8.self_attn.k_norm.weight": "model.safetensors",
225
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
226
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
227
+ "model.layers.8.self_attn.q_norm.weight": "model.safetensors",
228
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
229
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
230
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
231
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
232
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
233
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
234
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
235
+ "model.layers.9.post_feedforward_layernorm.weight": "model.safetensors",
236
+ "model.layers.9.pre_feedforward_layernorm.weight": "model.safetensors",
237
+ "model.layers.9.self_attn.k_norm.weight": "model.safetensors",
238
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
239
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
240
+ "model.layers.9.self_attn.q_norm.weight": "model.safetensors",
241
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
242
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
243
+ "model.norm.weight": "model.safetensors"
244
+ }
245
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff