Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+license: llama4
+library_name: mlx
+base_model: deepcogito/cogito-v2-preview-llama-109B-MoE
+tags:
+- mlx
+pipeline_tag: text-generation
+---
+
+# cogito-v2-preview-llama-109B-MoE-q4-hi-mlx
+
+This model [cogito-v2-preview-llama-109B-MoE-q4-hi-mlx](https://huggingface.co/cogito-v2-preview-llama-109B-MoE-q4-hi-mlx) was
+converted to MLX format from [deepcogito/cogito-v2-preview-llama-109B-MoE](https://huggingface.co/deepcogito/cogito-v2-preview-llama-109B-MoE)
+using mlx-lm version **0.26.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("cogito-v2-preview-llama-109B-MoE-q4-hi-mlx")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,150 @@
+{{- bos_token }}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- if not enable_thinking is defined %}
+    {%- set enable_thinking = false %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}    
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content']|trim %}
+    {%- else %}
+        {%- set system_message = messages[0]['content'][0]['text']|trim %}
+    {%- endif %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- Set the system message. If enable_thinking is true, add the "Enable deep thinking subroutine." #}
+{%- if enable_thinking %}
+    {%- if system_message != "" %}
+        {%- set system_message = "Enable deep thinking subroutine.
+
+" ~ system_message %}
+    {%- else %}
+        {%- set system_message = "Enable deep thinking subroutine." %}
+    {%- endif %}
+{%- endif %}
+
+{#- System message + tools #}
+{%- if tools is not none or system_message != '' %}
+    {{- "<|header_start|>system<|header_end|>
+
+" }}
+    {{- system_message }}
+    {%- if tools is not none %}
+        {%- if system_message != "" %}
+            {{- "
+
+" }}
+        {%- endif %}
+        {{- "Available Tools:
+" }}
+        {%- for t in tools %}
+            {{- t | tojson(indent=4) }}
+            {{- "
+
+" }}
+        {%- endfor %}
+    {%- endif %}
+    {{- "<|eot|>" }}
+{%- endif %}
+
+{#- Rest of the messages #}
+{%- for message in messages %}
+    {#- Case 1 - Usual, non tool related message. #}
+    {%- if not (message.role == "ipython" or message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {{- '<|header_start|>' + message['role'] + '<|header_end|>
+
+' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    
+    {#- Case 2 - the response is from the assistant, but has a tool call returned. #}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "<|header_start|>assistant<|header_end|>
+
+" }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+            {%- if message['content'] | trim != "" %}
+                {{- "
+
+" }}
+            {%- endif %}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                    {%- if content['text'] | trim != "" %}
+                        {{- "
+
+" }}
+                    {%- endif %}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- "[" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set out = tool_call.function|tojson %}
+                {%- if not tool_call.id is defined %}
+                    {{- out }}
+                {%- else %}
+                    {{- out[:-1] }}
+                    {{- ', "id": "' + tool_call.id + '"}' }}
+                {%- endif %}
+            {%- else %}
+                {{- tool_call|tojson }}
+            {%- endif %}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]<|eot|>" }}
+            {%- endif %}
+        {%- endfor %}
+    
+    {#- Case 3 - the response is from a tool call. #}
+    {%- elif message.role == "ipython" or message["role"] == "tool_results" or message["role"] == "tool" %}
+        {{- "<|header_start|>ipython<|header_end|>
+
+" }}
+        {%- if message.tool_call_id is defined and message.tool_call_id != '' %}
+            {{- '{"content": ' }}
+            {%- if message.content is mapping or (message.content is iterable and not message.content is string) %}
+                {{- message.content | tojson }}
+            {%- else %}
+                {{- '"' ~ message.content ~ '"' }}
+            {%- endif %}
+            {{- ', "call_id": "' ~ message.tool_call_id ~ '"}' }}
+        {%- else %}
+            {%- if message.content is mapping or (message.content is iterable and not message.content is string) %}
+                {{- message.content | tojson }}
+            {%- else %}
+                {{- message.content }}
+            {%- endif %}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|header_start|>assistant<|header_end|>\n\n' }}
+    {%- if enable_thinking %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,216 @@
+{
+    "architectures": [
+        "Llama4ForConditionalGeneration"
+    ],
+    "boi_token_index": 200080,
+    "eoi_token_index": 200081,
+    "image_token_index": 200092,
+    "model_type": "llama4",
+    "quantization": {
+        "group_size": 32,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4
+    },
+    "text_config": {
+        "attention_bias": false,
+        "attention_chunk_size": 8192,
+        "attention_dropout": 0.0,
+        "attn_scale": 0.1,
+        "attn_temperature_tuning": true,
+        "bos_token_id": 200000,
+        "eos_token_id": [
+            200001,
+            200007,
+            200008
+        ],
+        "floor_scale": 8192,
+        "for_llm_compressor": false,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 5120,
+        "initializer_range": 0.02,
+        "interleave_moe_layer_step": 1,
+        "intermediate_size": 8192,
+        "intermediate_size_mlp": 16384,
+        "layer_types": [
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "chunked_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 262144,
+        "model_type": "llama4_text",
+        "moe_layers": [
+            0,
+            1,
+            2,
+            3,
+            4,
+            5,
+            6,
+            7,
+            8,
+            9,
+            10,
+            11,
+            12,
+            13,
+            14,
+            15,
+            16,
+            17,
+            18,
+            19,
+            20,
+            21,
+            22,
+            23,
+            24,
+            25,
+            26,
+            27,
+            28,
+            29,
+            30,
+            31,
+            32,
+            33,
+            34,
+            35,
+            36,
+            37,
+            38,
+            39,
+            40,
+            41,
+            42,
+            43,
+            44,
+            45,
+            46,
+            47
+        ],
+        "no_rope_layers": [
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0,
+            1,
+            1,
+            1,
+            0
+        ],
+        "num_attention_heads": 40,
+        "num_experts_per_tok": 1,
+        "num_hidden_layers": 48,
+        "num_key_value_heads": 8,
+        "num_local_experts": 16,
+        "output_router_logits": false,
+        "pad_token_id": 200018,
+        "rms_norm_eps": 1e-05,
+        "rope_scaling": {
+            "factor": 16.0,
+            "high_freq_factor": 1.0,
+            "low_freq_factor": 1.0,
+            "original_max_position_embeddings": 8192,
+            "rope_type": "llama3"
+        },
+        "rope_theta": 500000.0,
+        "router_aux_loss_coef": 0.001,
+        "router_jitter_noise": 0.0,
+        "torch_dtype": "bfloat16",
+        "use_cache": true,
+        "use_qk_norm": true,
+        "vocab_size": 201135
+    },
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.53.0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a7f2c886faf3281458d85606d225e3446832384284dac9a6f9f89a9d13de6a
+size 5231384095

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c0e677c5bb94ea68f950c8350308017e3aba8821e62bc2cfaa29d89db1770e3
+size 5085899397

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d6fda61a001b08ed6b4b50ba07da71d77643df3696756115cf8ec79fd31f9b
+size 5345347101

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1162d083ecef505caa973654adc4c1643b6caf06bdbfd1f222fa34e71bfd546d
+size 5127842756

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a722a053e0c949665a8c48d4c6c2cc6821726b513166b3519b98a59995e77d5b
+size 5085899552

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ae3dcd526d432b7454237b4e1edc31f467743c99f3026b020d618f6ccc0abd
+size 5085899514

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6336882066e46a32f8f509d612c4be3e17f2e2d27b6ddbc085aa4c9e30a283
+size 5345347208

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa59988d2e91f52addc0afcb2533ef18ecdf4c6918a285ae045cc3fa64ad1dfc
+size 5127842772

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608180bc36ed5461d47981dd4454e3623ab8c90ee1730db30950908015c4fe6c
+size 5085899606

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57db6bc4608e968fe5375f7ad0ad0ae01ba5aa7dc634cdd93fb7b24aeafd708
+size 5085899538

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876793c52502e61bee5c22d556403d44b378f4415670df3f02f3300a293b8e54
+size 5345347178

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a58531dd2bbfc7fba953090e14f65faabe4bd442263c95a975477ddd2d60f658
+size 5127842774

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61a5ade4af0f1a67925c3a33c9cf5d60c333b47f1798d7ce9771caf3c75fa08
+size 5270788266

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
+size 27948578