add model

.gitattributes

@@ -33,3 +33,5 @@ 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
+tokenizer.model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -146,20 +146,20 @@ All evaluations are obtained through [lm-evaluation-harness](https://github.com/
 
 |                                                | Recovery (%) | meta-llama/Llama-4-Scout-17B-16E-Instruct | RedHatAI/Llama-4-Scout-17B-16E-Instruct-quantized.w4a16<br>(this model) |
 | ---------------------------------------------- | :-----------: | :---------------------------------------: | :-----------------------------------------------------------------: |
-| ARC-Challenge<br>25-shot                       | ?       | 69.37                                     | ?                                                               |
-| GSM8k<br>5-shot                                | ?        | 90.45                                     | ?                                                               |
-| HellaSwag<br>10-shot                           | ?        | 85.23                                     | ?                                                               |
-| MMLU<br>5-shot                                 | ?        | 80.54                                     | ?                                                               |
-| TruthfulQA<br>0-shot                           | ?        | 61.41                                     | ?                                                               |
-| WinoGrande<br>5-shot                           | ?        | 77.90                                     | ?                                                               |
-| **OpenLLM v1<br>Average Score**                    | **?**        | **77.48**                                     | **?**                                                               |
-| IFEval<br>0-shot<br>avg of inst and prompt acc | ?       | 86.90                                     | ?                                                               |
-| Big Bench Hard<br>3-shot                       | ?        | 65.13                                     | ?                                                               |
-| Math Lvl 5<br>4-shot                           | ?        | 57.78                                     | ?                                                               |
-| GPQA<br>0-shot                                 | ?       | 31.88                                     | ?                                                               |
-| MuSR<br>0-shot                                 | ?       | 42.20                                     | ?                                                               |
-| MMLU-Pro<br>5-shot                             | ?        | 55.70                                     | ?                                                               |
-| **OpenLLM v2<br>Average Score**                    | **?**       | **56.60**                                     | **?**                                                               |
+| ARC-Challenge<br>25-shot                       | 98.64       | 69.37                                     | 68.43                                                               |
+| GSM8k<br>5-shot                                | 98.99        | 90.45                                     | 89.54                                                               |
+| HellaSwag<br>10-shot                           | 99.91        | 85.23                                     | 85.15                                                               |
+| MMLU<br>5-shot                                 | 99.70        | 80.54                                     | 80.30                                                               |
+| TruthfulQA<br>0-shot                           | 99.44        | 61.41                                     | 61.07                                                               |
+| WinoGrande<br>5-shot                           | 100.2        | 77.90                                     | 78.06                                                               |
+| **OpenLLM v1<br>Average Score**                    | **99.00**        | **77.48**                                     | **77.09**                                                               |
+| IFEval<br>0-shot<br>avg of inst and prompt acc | 100.6       | 86.90                                     | 87.45                                                               |
+| Big Bench Hard<br>3-shot                       | 99.78        | 65.13                                     | 64.99                                                               |
+| Math Lvl 5<br>4-shot                           | 100.6        | 57.78                                     | 58.16                                                               |
+| GPQA<br>0-shot                                 | 102.6       | 31.88                                     | 32.72                                                               |
+| MuSR<br>0-shot                                 | 101.2       | 42.20                                     | 42.72                                                               |
+| MMLU-Pro<br>5-shot                             | 99.12        | 55.70                                     | 55.21                                                               |
+| **OpenLLM v2<br>Average Score**                    | **100.48**       | **56.60**                                     | **56.87**                                                               |
 | RULER<br>seqlen = 131072<br>niah_multikey_1    | ?       | 88.20                                     | ?                                                               |
 | RULER<br>seqlen = 131072<br>niah_multikey_2    | ?       | 83.60                                     | ?                                                               |
 | RULER<br>seqlen = 131072<br>niah_multikey_3    | ?        | 78.80                                     | ?                                                               |
@@ -174,7 +174,7 @@ All evaluations are obtained through [lm-evaluation-harness](https://github.com/
 | RULER<br>seqlen = 131072<br>ruler_qa_squad     | ?        | 53.57                                     | ?                                                               |
 | RULER<br>seqlen = 131072<br>ruler_qa_vt        | ?       | 92.28                                     | ?                                                               |
 | **RULER<br>seqlen = 131072<br>Average Score**      | **?**        | **80.44**                                     | **?**                                                               |
-| MMMU<br>0-shot                                 | ?        | 53.44                                     | ?                                                               |
-| ChartQA<br>0-shot<br>exact_match               | ?       | 65.88                                     | ?                                                               |
-| ChartQA<br>0-shot<br>relaxed_accuracy          | ?        | 88.92                                     | ?                                                               |
-| **Multimodal Average Score**                       | **?**        | **69.41**                                     | **?**                                                               |
+| MMMU<br>0-shot                                 | 101.6        | 53.44                                     | 54.33                                                               |
+| ChartQA<br>0-shot<br>exact_match               | 100.8       | 65.88                                     | 66.44                                                               |
+| ChartQA<br>0-shot<br>relaxed_accuracy          | 99.82        | 88.92                                     | 88.76                                                               |
+| **Multimodal Average Score**                       | **100.2**        | **69.41**                                     | **77.60**                                                               |

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}    \n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content']|trim %}\n    {%- else %}\n        {#- FIXME: The processor requires an array, always. #}\n        {%- set system_message = messages[0]['content'][0]['text']|trim %}\n    {%- endif %}\n    {%- set messages = messages[1:] %}\n    {%- set user_supplied_system_message = true %}\n{%- else %}\n    {%- set system_message = \"\" %}\n    {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- System message if the user supplied one #}\n{%- if user_supplied_system_message %}\n    {{- \"<|header_start|>system<|header_end|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|header_start|>user<|header_end|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|header_start|>' + message['role'] + '<|header_end|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}\n       {{- '<|header_start|>assistant<|header_end|>\\n\\n' -}}\n       {{- '<|python_start|>' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n       {{- '<|python_end|>' }}\n        {%- for tool_call in message.tool_calls %}\n           {{- '{\"name\": \"' + tool_call.function.name + '\", ' }}\n           {{- '\"parameters\": ' }}\n           {{- tool_call.function.arguments | tojson }}\n           {{- \"}\" }}\n        {%- endfor %}\n       {{- \"<|eot|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|header_start|>ipython<|header_end|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|header_start|>assistant<|header_end|>\\n\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,559 @@
+{
+  "architectures": [
+    "Llama4ForConditionalGeneration"
+  ],
+  "boi_token_index": 200080,
+  "eoi_token_index": 200081,
+  "image_token_index": 200092,
+  "model_type": "llama4",
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_chunk_size": 8192,
+    "attention_dropout": 0.0,
+    "bos_token_id": 200000,
+    "eos_token_id": [
+      200001,
+      200007,
+      200008
+    ],
+    "for_llm_compressor": true,
+    "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,
+    "max_position_embeddings": 10485760,
+    "model_type": "llama4_text",
+    "no_rope_layers": [],
+    "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": 202048
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0.dev0",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 336,
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "model_type": "llama4_vision_model",
+    "multi_modal_projector_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 34,
+    "patch_size": 14,
+    "pixel_shuffle_ratio": 0.5,
+    "projector_dropout": 0.0,
+    "projector_input_dim": 4096,
+    "projector_output_dim": 4096,
+    "rope_theta": 10000,
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "default",
+    "vision_output_dim": 4096
+  },
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": "weight",
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "vision_model.patch_embedding.linear",
+      "vision_model.model.layers.0.self_attn.q_proj",
+      "vision_model.model.layers.0.self_attn.k_proj",
+      "vision_model.model.layers.0.self_attn.v_proj",
+      "vision_model.model.layers.0.self_attn.o_proj",
+      "vision_model.model.layers.0.mlp.fc1",
+      "vision_model.model.layers.0.mlp.fc2",
+      "vision_model.model.layers.1.self_attn.q_proj",
+      "vision_model.model.layers.1.self_attn.k_proj",
+      "vision_model.model.layers.1.self_attn.v_proj",
+      "vision_model.model.layers.1.self_attn.o_proj",
+      "vision_model.model.layers.1.mlp.fc1",
+      "vision_model.model.layers.1.mlp.fc2",
+      "vision_model.model.layers.2.self_attn.q_proj",
+      "vision_model.model.layers.2.self_attn.k_proj",
+      "vision_model.model.layers.2.self_attn.v_proj",
+      "vision_model.model.layers.2.self_attn.o_proj",
+      "vision_model.model.layers.2.mlp.fc1",
+      "vision_model.model.layers.2.mlp.fc2",
+      "vision_model.model.layers.3.self_attn.q_proj",
+      "vision_model.model.layers.3.self_attn.k_proj",
+      "vision_model.model.layers.3.self_attn.v_proj",
+      "vision_model.model.layers.3.self_attn.o_proj",
+      "vision_model.model.layers.3.mlp.fc1",
+      "vision_model.model.layers.3.mlp.fc2",
+      "vision_model.model.layers.4.self_attn.q_proj",
+      "vision_model.model.layers.4.self_attn.k_proj",
+      "vision_model.model.layers.4.self_attn.v_proj",
+      "vision_model.model.layers.4.self_attn.o_proj",
+      "vision_model.model.layers.4.mlp.fc1",
+      "vision_model.model.layers.4.mlp.fc2",
+      "vision_model.model.layers.5.self_attn.q_proj",
+      "vision_model.model.layers.5.self_attn.k_proj",
+      "vision_model.model.layers.5.self_attn.v_proj",
+      "vision_model.model.layers.5.self_attn.o_proj",
+      "vision_model.model.layers.5.mlp.fc1",
+      "vision_model.model.layers.5.mlp.fc2",
+      "vision_model.model.layers.6.self_attn.q_proj",
+      "vision_model.model.layers.6.self_attn.k_proj",
+      "vision_model.model.layers.6.self_attn.v_proj",
+      "vision_model.model.layers.6.self_attn.o_proj",
+      "vision_model.model.layers.6.mlp.fc1",
+      "vision_model.model.layers.6.mlp.fc2",
+      "vision_model.model.layers.7.self_attn.q_proj",
+      "vision_model.model.layers.7.self_attn.k_proj",
+      "vision_model.model.layers.7.self_attn.v_proj",
+      "vision_model.model.layers.7.self_attn.o_proj",
+      "vision_model.model.layers.7.mlp.fc1",
+      "vision_model.model.layers.7.mlp.fc2",
+      "vision_model.model.layers.8.self_attn.q_proj",
+      "vision_model.model.layers.8.self_attn.k_proj",
+      "vision_model.model.layers.8.self_attn.v_proj",
+      "vision_model.model.layers.8.self_attn.o_proj",
+      "vision_model.model.layers.8.mlp.fc1",
+      "vision_model.model.layers.8.mlp.fc2",
+      "vision_model.model.layers.9.self_attn.q_proj",
+      "vision_model.model.layers.9.self_attn.k_proj",
+      "vision_model.model.layers.9.self_attn.v_proj",
+      "vision_model.model.layers.9.self_attn.o_proj",
+      "vision_model.model.layers.9.mlp.fc1",
+      "vision_model.model.layers.9.mlp.fc2",
+      "vision_model.model.layers.10.self_attn.q_proj",
+      "vision_model.model.layers.10.self_attn.k_proj",
+      "vision_model.model.layers.10.self_attn.v_proj",
+      "vision_model.model.layers.10.self_attn.o_proj",
+      "vision_model.model.layers.10.mlp.fc1",
+      "vision_model.model.layers.10.mlp.fc2",
+      "vision_model.model.layers.11.self_attn.q_proj",
+      "vision_model.model.layers.11.self_attn.k_proj",
+      "vision_model.model.layers.11.self_attn.v_proj",
+      "vision_model.model.layers.11.self_attn.o_proj",
+      "vision_model.model.layers.11.mlp.fc1",
+      "vision_model.model.layers.11.mlp.fc2",
+      "vision_model.model.layers.12.self_attn.q_proj",
+      "vision_model.model.layers.12.self_attn.k_proj",
+      "vision_model.model.layers.12.self_attn.v_proj",
+      "vision_model.model.layers.12.self_attn.o_proj",
+      "vision_model.model.layers.12.mlp.fc1",
+      "vision_model.model.layers.12.mlp.fc2",
+      "vision_model.model.layers.13.self_attn.q_proj",
+      "vision_model.model.layers.13.self_attn.k_proj",
+      "vision_model.model.layers.13.self_attn.v_proj",
+      "vision_model.model.layers.13.self_attn.o_proj",
+      "vision_model.model.layers.13.mlp.fc1",
+      "vision_model.model.layers.13.mlp.fc2",
+      "vision_model.model.layers.14.self_attn.q_proj",
+      "vision_model.model.layers.14.self_attn.k_proj",
+      "vision_model.model.layers.14.self_attn.v_proj",
+      "vision_model.model.layers.14.self_attn.o_proj",
+      "vision_model.model.layers.14.mlp.fc1",
+      "vision_model.model.layers.14.mlp.fc2",
+      "vision_model.model.layers.15.self_attn.q_proj",
+      "vision_model.model.layers.15.self_attn.k_proj",
+      "vision_model.model.layers.15.self_attn.v_proj",
+      "vision_model.model.layers.15.self_attn.o_proj",
+      "vision_model.model.layers.15.mlp.fc1",
+      "vision_model.model.layers.15.mlp.fc2",
+      "vision_model.model.layers.16.self_attn.q_proj",
+      "vision_model.model.layers.16.self_attn.k_proj",
+      "vision_model.model.layers.16.self_attn.v_proj",
+      "vision_model.model.layers.16.self_attn.o_proj",
+      "vision_model.model.layers.16.mlp.fc1",
+      "vision_model.model.layers.16.mlp.fc2",
+      "vision_model.model.layers.17.self_attn.q_proj",
+      "vision_model.model.layers.17.self_attn.k_proj",
+      "vision_model.model.layers.17.self_attn.v_proj",
+      "vision_model.model.layers.17.self_attn.o_proj",
+      "vision_model.model.layers.17.mlp.fc1",
+      "vision_model.model.layers.17.mlp.fc2",
+      "vision_model.model.layers.18.self_attn.q_proj",
+      "vision_model.model.layers.18.self_attn.k_proj",
+      "vision_model.model.layers.18.self_attn.v_proj",
+      "vision_model.model.layers.18.self_attn.o_proj",
+      "vision_model.model.layers.18.mlp.fc1",
+      "vision_model.model.layers.18.mlp.fc2",
+      "vision_model.model.layers.19.self_attn.q_proj",
+      "vision_model.model.layers.19.self_attn.k_proj",
+      "vision_model.model.layers.19.self_attn.v_proj",
+      "vision_model.model.layers.19.self_attn.o_proj",
+      "vision_model.model.layers.19.mlp.fc1",
+      "vision_model.model.layers.19.mlp.fc2",
+      "vision_model.model.layers.20.self_attn.q_proj",
+      "vision_model.model.layers.20.self_attn.k_proj",
+      "vision_model.model.layers.20.self_attn.v_proj",
+      "vision_model.model.layers.20.self_attn.o_proj",
+      "vision_model.model.layers.20.mlp.fc1",
+      "vision_model.model.layers.20.mlp.fc2",
+      "vision_model.model.layers.21.self_attn.q_proj",
+      "vision_model.model.layers.21.self_attn.k_proj",
+      "vision_model.model.layers.21.self_attn.v_proj",
+      "vision_model.model.layers.21.self_attn.o_proj",
+      "vision_model.model.layers.21.mlp.fc1",
+      "vision_model.model.layers.21.mlp.fc2",
+      "vision_model.model.layers.22.self_attn.q_proj",
+      "vision_model.model.layers.22.self_attn.k_proj",
+      "vision_model.model.layers.22.self_attn.v_proj",
+      "vision_model.model.layers.22.self_attn.o_proj",
+      "vision_model.model.layers.22.mlp.fc1",
+      "vision_model.model.layers.22.mlp.fc2",
+      "vision_model.model.layers.23.self_attn.q_proj",
+      "vision_model.model.layers.23.self_attn.k_proj",
+      "vision_model.model.layers.23.self_attn.v_proj",
+      "vision_model.model.layers.23.self_attn.o_proj",
+      "vision_model.model.layers.23.mlp.fc1",
+      "vision_model.model.layers.23.mlp.fc2",
+      "vision_model.model.layers.24.self_attn.q_proj",
+      "vision_model.model.layers.24.self_attn.k_proj",
+      "vision_model.model.layers.24.self_attn.v_proj",
+      "vision_model.model.layers.24.self_attn.o_proj",
+      "vision_model.model.layers.24.mlp.fc1",
+      "vision_model.model.layers.24.mlp.fc2",
+      "vision_model.model.layers.25.self_attn.q_proj",
+      "vision_model.model.layers.25.self_attn.k_proj",
+      "vision_model.model.layers.25.self_attn.v_proj",
+      "vision_model.model.layers.25.self_attn.o_proj",
+      "vision_model.model.layers.25.mlp.fc1",
+      "vision_model.model.layers.25.mlp.fc2",
+      "vision_model.model.layers.26.self_attn.q_proj",
+      "vision_model.model.layers.26.self_attn.k_proj",
+      "vision_model.model.layers.26.self_attn.v_proj",
+      "vision_model.model.layers.26.self_attn.o_proj",
+      "vision_model.model.layers.26.mlp.fc1",
+      "vision_model.model.layers.26.mlp.fc2",
+      "vision_model.model.layers.27.self_attn.q_proj",
+      "vision_model.model.layers.27.self_attn.k_proj",
+      "vision_model.model.layers.27.self_attn.v_proj",
+      "vision_model.model.layers.27.self_attn.o_proj",
+      "vision_model.model.layers.27.mlp.fc1",
+      "vision_model.model.layers.27.mlp.fc2",
+      "vision_model.model.layers.28.self_attn.q_proj",
+      "vision_model.model.layers.28.self_attn.k_proj",
+      "vision_model.model.layers.28.self_attn.v_proj",
+      "vision_model.model.layers.28.self_attn.o_proj",
+      "vision_model.model.layers.28.mlp.fc1",
+      "vision_model.model.layers.28.mlp.fc2",
+      "vision_model.model.layers.29.self_attn.q_proj",
+      "vision_model.model.layers.29.self_attn.k_proj",
+      "vision_model.model.layers.29.self_attn.v_proj",
+      "vision_model.model.layers.29.self_attn.o_proj",
+      "vision_model.model.layers.29.mlp.fc1",
+      "vision_model.model.layers.29.mlp.fc2",
+      "vision_model.model.layers.30.self_attn.q_proj",
+      "vision_model.model.layers.30.self_attn.k_proj",
+      "vision_model.model.layers.30.self_attn.v_proj",
+      "vision_model.model.layers.30.self_attn.o_proj",
+      "vision_model.model.layers.30.mlp.fc1",
+      "vision_model.model.layers.30.mlp.fc2",
+      "vision_model.model.layers.31.self_attn.q_proj",
+      "vision_model.model.layers.31.self_attn.k_proj",
+      "vision_model.model.layers.31.self_attn.v_proj",
+      "vision_model.model.layers.31.self_attn.o_proj",
+      "vision_model.model.layers.31.mlp.fc1",
+      "vision_model.model.layers.31.mlp.fc2",
+      "vision_model.model.layers.32.self_attn.q_proj",
+      "vision_model.model.layers.32.self_attn.k_proj",
+      "vision_model.model.layers.32.self_attn.v_proj",
+      "vision_model.model.layers.32.self_attn.o_proj",
+      "vision_model.model.layers.32.mlp.fc1",
+      "vision_model.model.layers.32.mlp.fc2",
+      "vision_model.model.layers.33.self_attn.q_proj",
+      "vision_model.model.layers.33.self_attn.k_proj",
+      "vision_model.model.layers.33.self_attn.v_proj",
+      "vision_model.model.layers.33.self_attn.o_proj",
+      "vision_model.model.layers.33.mlp.fc1",
+      "vision_model.model.layers.33.mlp.fc2",
+      "vision_model.vision_adapter.mlp.fc1",
+      "vision_model.vision_adapter.mlp.fc2",
+      "multi_modal_projector.linear_1",
+      "language_model.model.layers.0.self_attn.q_proj",
+      "language_model.model.layers.0.self_attn.k_proj",
+      "language_model.model.layers.0.self_attn.v_proj",
+      "language_model.model.layers.0.self_attn.o_proj",
+      "language_model.model.layers.0.feed_forward.router",
+      "language_model.model.layers.1.self_attn.q_proj",
+      "language_model.model.layers.1.self_attn.k_proj",
+      "language_model.model.layers.1.self_attn.v_proj",
+      "language_model.model.layers.1.self_attn.o_proj",
+      "language_model.model.layers.1.feed_forward.router",
+      "language_model.model.layers.2.self_attn.q_proj",
+      "language_model.model.layers.2.self_attn.k_proj",
+      "language_model.model.layers.2.self_attn.v_proj",
+      "language_model.model.layers.2.self_attn.o_proj",
+      "language_model.model.layers.2.feed_forward.router",
+      "language_model.model.layers.3.self_attn.q_proj",
+      "language_model.model.layers.3.self_attn.k_proj",
+      "language_model.model.layers.3.self_attn.v_proj",
+      "language_model.model.layers.3.self_attn.o_proj",
+      "language_model.model.layers.3.feed_forward.router",
+      "language_model.model.layers.4.self_attn.q_proj",
+      "language_model.model.layers.4.self_attn.k_proj",
+      "language_model.model.layers.4.self_attn.v_proj",
+      "language_model.model.layers.4.self_attn.o_proj",
+      "language_model.model.layers.4.feed_forward.router",
+      "language_model.model.layers.5.self_attn.q_proj",
+      "language_model.model.layers.5.self_attn.k_proj",
+      "language_model.model.layers.5.self_attn.v_proj",
+      "language_model.model.layers.5.self_attn.o_proj",
+      "language_model.model.layers.5.feed_forward.router",
+      "language_model.model.layers.6.self_attn.q_proj",
+      "language_model.model.layers.6.self_attn.k_proj",
+      "language_model.model.layers.6.self_attn.v_proj",
+      "language_model.model.layers.6.self_attn.o_proj",
+      "language_model.model.layers.6.feed_forward.router",
+      "language_model.model.layers.7.self_attn.q_proj",
+      "language_model.model.layers.7.self_attn.k_proj",
+      "language_model.model.layers.7.self_attn.v_proj",
+      "language_model.model.layers.7.self_attn.o_proj",
+      "language_model.model.layers.7.feed_forward.router",
+      "language_model.model.layers.8.self_attn.q_proj",
+      "language_model.model.layers.8.self_attn.k_proj",
+      "language_model.model.layers.8.self_attn.v_proj",
+      "language_model.model.layers.8.self_attn.o_proj",
+      "language_model.model.layers.8.feed_forward.router",
+      "language_model.model.layers.9.self_attn.q_proj",
+      "language_model.model.layers.9.self_attn.k_proj",
+      "language_model.model.layers.9.self_attn.v_proj",
+      "language_model.model.layers.9.self_attn.o_proj",
+      "language_model.model.layers.9.feed_forward.router",
+      "language_model.model.layers.10.self_attn.q_proj",
+      "language_model.model.layers.10.self_attn.k_proj",
+      "language_model.model.layers.10.self_attn.v_proj",
+      "language_model.model.layers.10.self_attn.o_proj",
+      "language_model.model.layers.10.feed_forward.router",
+      "language_model.model.layers.11.self_attn.q_proj",
+      "language_model.model.layers.11.self_attn.k_proj",
+      "language_model.model.layers.11.self_attn.v_proj",
+      "language_model.model.layers.11.self_attn.o_proj",
+      "language_model.model.layers.11.feed_forward.router",
+      "language_model.model.layers.12.self_attn.q_proj",
+      "language_model.model.layers.12.self_attn.k_proj",
+      "language_model.model.layers.12.self_attn.v_proj",
+      "language_model.model.layers.12.self_attn.o_proj",
+      "language_model.model.layers.12.feed_forward.router",
+      "language_model.model.layers.13.self_attn.q_proj",
+      "language_model.model.layers.13.self_attn.k_proj",
+      "language_model.model.layers.13.self_attn.v_proj",
+      "language_model.model.layers.13.self_attn.o_proj",
+      "language_model.model.layers.13.feed_forward.router",
+      "language_model.model.layers.14.self_attn.q_proj",
+      "language_model.model.layers.14.self_attn.k_proj",
+      "language_model.model.layers.14.self_attn.v_proj",
+      "language_model.model.layers.14.self_attn.o_proj",
+      "language_model.model.layers.14.feed_forward.router",
+      "language_model.model.layers.15.self_attn.q_proj",
+      "language_model.model.layers.15.self_attn.k_proj",
+      "language_model.model.layers.15.self_attn.v_proj",
+      "language_model.model.layers.15.self_attn.o_proj",
+      "language_model.model.layers.15.feed_forward.router",
+      "language_model.model.layers.16.self_attn.q_proj",
+      "language_model.model.layers.16.self_attn.k_proj",
+      "language_model.model.layers.16.self_attn.v_proj",
+      "language_model.model.layers.16.self_attn.o_proj",
+      "language_model.model.layers.16.feed_forward.router",
+      "language_model.model.layers.17.self_attn.q_proj",
+      "language_model.model.layers.17.self_attn.k_proj",
+      "language_model.model.layers.17.self_attn.v_proj",
+      "language_model.model.layers.17.self_attn.o_proj",
+      "language_model.model.layers.17.feed_forward.router",
+      "language_model.model.layers.18.self_attn.q_proj",
+      "language_model.model.layers.18.self_attn.k_proj",
+      "language_model.model.layers.18.self_attn.v_proj",
+      "language_model.model.layers.18.self_attn.o_proj",
+      "language_model.model.layers.18.feed_forward.router",
+      "language_model.model.layers.19.self_attn.q_proj",
+      "language_model.model.layers.19.self_attn.k_proj",
+      "language_model.model.layers.19.self_attn.v_proj",
+      "language_model.model.layers.19.self_attn.o_proj",
+      "language_model.model.layers.19.feed_forward.router",
+      "language_model.model.layers.20.self_attn.q_proj",
+      "language_model.model.layers.20.self_attn.k_proj",
+      "language_model.model.layers.20.self_attn.v_proj",
+      "language_model.model.layers.20.self_attn.o_proj",
+      "language_model.model.layers.20.feed_forward.router",
+      "language_model.model.layers.21.self_attn.q_proj",
+      "language_model.model.layers.21.self_attn.k_proj",
+      "language_model.model.layers.21.self_attn.v_proj",
+      "language_model.model.layers.21.self_attn.o_proj",
+      "language_model.model.layers.21.feed_forward.router",
+      "language_model.model.layers.22.self_attn.q_proj",
+      "language_model.model.layers.22.self_attn.k_proj",
+      "language_model.model.layers.22.self_attn.v_proj",
+      "language_model.model.layers.22.self_attn.o_proj",
+      "language_model.model.layers.22.feed_forward.router",
+      "language_model.model.layers.23.self_attn.q_proj",
+      "language_model.model.layers.23.self_attn.k_proj",
+      "language_model.model.layers.23.self_attn.v_proj",
+      "language_model.model.layers.23.self_attn.o_proj",
+      "language_model.model.layers.23.feed_forward.router",
+      "language_model.model.layers.24.self_attn.q_proj",
+      "language_model.model.layers.24.self_attn.k_proj",
+      "language_model.model.layers.24.self_attn.v_proj",
+      "language_model.model.layers.24.self_attn.o_proj",
+      "language_model.model.layers.24.feed_forward.router",
+      "language_model.model.layers.25.self_attn.q_proj",
+      "language_model.model.layers.25.self_attn.k_proj",
+      "language_model.model.layers.25.self_attn.v_proj",
+      "language_model.model.layers.25.self_attn.o_proj",
+      "language_model.model.layers.25.feed_forward.router",
+      "language_model.model.layers.26.self_attn.q_proj",
+      "language_model.model.layers.26.self_attn.k_proj",
+      "language_model.model.layers.26.self_attn.v_proj",
+      "language_model.model.layers.26.self_attn.o_proj",
+      "language_model.model.layers.26.feed_forward.router",
+      "language_model.model.layers.27.self_attn.q_proj",
+      "language_model.model.layers.27.self_attn.k_proj",
+      "language_model.model.layers.27.self_attn.v_proj",
+      "language_model.model.layers.27.self_attn.o_proj",
+      "language_model.model.layers.27.feed_forward.router",
+      "language_model.model.layers.28.self_attn.q_proj",
+      "language_model.model.layers.28.self_attn.k_proj",
+      "language_model.model.layers.28.self_attn.v_proj",
+      "language_model.model.layers.28.self_attn.o_proj",
+      "language_model.model.layers.28.feed_forward.router",
+      "language_model.model.layers.29.self_attn.q_proj",
+      "language_model.model.layers.29.self_attn.k_proj",
+      "language_model.model.layers.29.self_attn.v_proj",
+      "language_model.model.layers.29.self_attn.o_proj",
+      "language_model.model.layers.29.feed_forward.router",
+      "language_model.model.layers.30.self_attn.q_proj",
+      "language_model.model.layers.30.self_attn.k_proj",
+      "language_model.model.layers.30.self_attn.v_proj",
+      "language_model.model.layers.30.self_attn.o_proj",
+      "language_model.model.layers.30.feed_forward.router",
+      "language_model.model.layers.31.self_attn.q_proj",
+      "language_model.model.layers.31.self_attn.k_proj",
+      "language_model.model.layers.31.self_attn.v_proj",
+      "language_model.model.layers.31.self_attn.o_proj",
+      "language_model.model.layers.31.feed_forward.router",
+      "language_model.model.layers.32.self_attn.q_proj",
+      "language_model.model.layers.32.self_attn.k_proj",
+      "language_model.model.layers.32.self_attn.v_proj",
+      "language_model.model.layers.32.self_attn.o_proj",
+      "language_model.model.layers.32.feed_forward.router",
+      "language_model.model.layers.33.self_attn.q_proj",
+      "language_model.model.layers.33.self_attn.k_proj",
+      "language_model.model.layers.33.self_attn.v_proj",
+      "language_model.model.layers.33.self_attn.o_proj",
+      "language_model.model.layers.33.feed_forward.router",
+      "language_model.model.layers.34.self_attn.q_proj",
+      "language_model.model.layers.34.self_attn.k_proj",
+      "language_model.model.layers.34.self_attn.v_proj",
+      "language_model.model.layers.34.self_attn.o_proj",
+      "language_model.model.layers.34.feed_forward.router",
+      "language_model.model.layers.35.self_attn.q_proj",
+      "language_model.model.layers.35.self_attn.k_proj",
+      "language_model.model.layers.35.self_attn.v_proj",
+      "language_model.model.layers.35.self_attn.o_proj",
+      "language_model.model.layers.35.feed_forward.router",
+      "language_model.model.layers.36.self_attn.q_proj",
+      "language_model.model.layers.36.self_attn.k_proj",
+      "language_model.model.layers.36.self_attn.v_proj",
+      "language_model.model.layers.36.self_attn.o_proj",
+      "language_model.model.layers.36.feed_forward.router",
+      "language_model.model.layers.37.self_attn.q_proj",
+      "language_model.model.layers.37.self_attn.k_proj",
+      "language_model.model.layers.37.self_attn.v_proj",
+      "language_model.model.layers.37.self_attn.o_proj",
+      "language_model.model.layers.37.feed_forward.router",
+      "language_model.model.layers.38.self_attn.q_proj",
+      "language_model.model.layers.38.self_attn.k_proj",
+      "language_model.model.layers.38.self_attn.v_proj",
+      "language_model.model.layers.38.self_attn.o_proj",
+      "language_model.model.layers.38.feed_forward.router",
+      "language_model.model.layers.39.self_attn.q_proj",
+      "language_model.model.layers.39.self_attn.k_proj",
+      "language_model.model.layers.39.self_attn.v_proj",
+      "language_model.model.layers.39.self_attn.o_proj",
+      "language_model.model.layers.39.feed_forward.router",
+      "language_model.model.layers.40.self_attn.q_proj",
+      "language_model.model.layers.40.self_attn.k_proj",
+      "language_model.model.layers.40.self_attn.v_proj",
+      "language_model.model.layers.40.self_attn.o_proj",
+      "language_model.model.layers.40.feed_forward.router",
+      "language_model.model.layers.41.self_attn.q_proj",
+      "language_model.model.layers.41.self_attn.k_proj",
+      "language_model.model.layers.41.self_attn.v_proj",
+      "language_model.model.layers.41.self_attn.o_proj",
+      "language_model.model.layers.41.feed_forward.router",
+      "language_model.model.layers.42.self_attn.q_proj",
+      "language_model.model.layers.42.self_attn.k_proj",
+      "language_model.model.layers.42.self_attn.v_proj",
+      "language_model.model.layers.42.self_attn.o_proj",
+      "language_model.model.layers.42.feed_forward.router",
+      "language_model.model.layers.43.self_attn.q_proj",
+      "language_model.model.layers.43.self_attn.k_proj",
+      "language_model.model.layers.43.self_attn.v_proj",
+      "language_model.model.layers.43.self_attn.o_proj",
+      "language_model.model.layers.43.feed_forward.router",
+      "language_model.model.layers.44.self_attn.q_proj",
+      "language_model.model.layers.44.self_attn.k_proj",
+      "language_model.model.layers.44.self_attn.v_proj",
+      "language_model.model.layers.44.self_attn.o_proj",
+      "language_model.model.layers.44.feed_forward.router",
+      "language_model.model.layers.45.self_attn.q_proj",
+      "language_model.model.layers.45.self_attn.k_proj",
+      "language_model.model.layers.45.self_attn.v_proj",
+      "language_model.model.layers.45.self_attn.o_proj",
+      "language_model.model.layers.45.feed_forward.router",
+      "language_model.model.layers.46.self_attn.q_proj",
+      "language_model.model.layers.46.self_attn.k_proj",
+      "language_model.model.layers.46.self_attn.v_proj",
+      "language_model.model.layers.46.self_attn.o_proj",
+      "language_model.model.layers.46.feed_forward.router",
+      "language_model.model.layers.47.self_attn.q_proj",
+      "language_model.model.layers.47.self_attn.k_proj",
+      "language_model.model.layers.47.self_attn.v_proj",
+      "language_model.model.layers.47.self_attn.o_proj",
+      "language_model.model.layers.47.feed_forward.router",
+      "language_model.lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 200000,
+  "do_sample": true,
+  "eos_token_id": [
+    200001,
+    200007,
+    200008
+  ],
+  "pad_token_id": 200018,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.0.dev0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ce5813ecfa1915201f7a2ded7595e42b6edb343692926fb7e8cca757db8575
+size 4998638648

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ca1a631427ce8e3a5ba839b98092159e97b59033972088c85bf5fb527a799f
+size 4959308680

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e880d5785420d723c560149dc0c561b150280a368d2e46146dc35706e312dd1
+size 4989434120

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502c1678435a66f4696040ec38b777d9b10ee0cc04195b0dee4a4acb790730bc
+size 4990090304

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49df15a28f95daaa0f9796687eddb67b87348fcbdb875b6e64748a291b5691f1
+size 4980916048

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48e04c79523a156536df01dcca2d879ea8363090fb926b44650f14af140ad383
+size 4980916048

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f72e8b7dd0ac06960e72c0b3d563a42ec26b64829fc06b30eac020408e9a2f
+size 4980916048

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8b9e02664811b0ab805c0c02c6604ac8d7df61454eaa59a80369ec532f28fc
+size 4980916048

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab179c6195ab988199154d52c275b7a1b4f990146b3764a9a06e796d2b9ee094
+size 4980916048

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0338b98b767b69a6f0408691db65712174916d809bfe632c3621ee5fb0d847e6
+size 4980916048

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd82b64e02b8bad0aeba3c5ef19bd14bbb0387dd8febafa001d293a6bbe00156
+size 4980916048

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9506596c2d50bbd394830da875437eafda8abc2262be15402c175ac4f7ba569
+size 4980916048

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3475d1aa719f980da467d32786e5acc445b766edf2f51ec082689dd6fd132f
+size 3020522640

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f412ae287747cc86e6ee5d58600bbe5c574d6fa77f351367aae9ea3f4dbcc3a
+size 2068971664

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Llama4ImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_patches": 16,
+  "processor_class": "Llama4Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "resize_to_max_canvas": false,
+  "return_tensors": null,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "fake_image_token": "<|image|>",
+  "image_token": "<|image|>",
+  "patch_size": 14,
+  "processor_class": "Llama4Processor"
+}

recipe.yaml

@@ -0,0 +1,11 @@
+default_stage:
+  default_modifiers:
+    GPTQModifier:
+      dampening_frac: 0.05
+      config_groups:
+        config_group:
+          targets: [Linear]
+          weights: {num_bits: 4, type: int, symmetric: true, group_size: 128, strategy: group,
+            dynamic: false, actorder: weight, observer: mse}
+      targets: Linear
+      ignore: ['re:.*lm_head', 're:.*self_attn', 're:.*router', 're:.*vision_model', 're:.*multi_modal_projector']

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot|>",
+  "pad_token": "<|finetune_right_pad_id|>"
+}

tokenizer.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bdbaf59b0762c8c807617e2d8ea51420eb1b1de266df2495be755c8e0ed6ed
+size 3622230