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 +1,68 @@
+---
+library_name: transformers
+tags:
+- prime-rl
+- verifiers
+- prime-intellect
+- reinforcement-learning
+- reasoning
+- agentic
+- mixture-of-experts
+license: mit
+language:
+- en
+base_model:
+- PrimeIntellect/INTELLECT-3.1
+pipeline_tag: text-generation
+---
+
+# INTELLECT-3.1
+
+<div align="center">
+<img src="https://huggingface.co/PrimeIntellect/INTELLECT-3/resolve/main/banner.png" alt="Prime Intellect Logo" />
+</div>
+
+<p align="center">
+    <strong>INTELLECT-3.1: A 100B+ MoE trained with large-scale RL</strong>
+    <br><br>
+    Trained with <a href="https://github.com/PrimeIntellect-ai/prime-rl">prime-rl</a> and <a href="https://github.com/PrimeIntellect-ai/verifiers">verifiers</a>
+    <br>
+    Environments released on <a href="https://app.primeintellect.ai/dashboard/environments">Environments Hub</a> 
+    <br>
+    Read the <a href="https://primeintellect.ai/blog/intellect-3">Blog</a> & <a href="https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf">Technical Report</a>
+    <br>
+    <a href="https://x.com/primeintellect">X</a>  | <a href="https://discord.gg/RC5GvMbfDf">Discord</a> | <a href="https://app.primeintellect.ai/dashboard/create-cluster">Prime Intellect Platform</a>
+</p>
+
+## Introduction
+
+**INTELLECT-3.1** is a 106B (A12B) parameter Mixture-of-Experts reasoning model built as a continued training of [INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3) with additional reinforcement learning on math, coding, software engineering, and agentic tasks.
+
+Training was performed with [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) using environments built with the [verifiers](https://github.com/PrimeIntellect-ai/verifiers) library.
+All training and evaluation environments are available on the [Environments Hub](https://app.primeintellect.ai/dashboard/environments).
+
+The model, training frameworks, and environments are open-sourced under fully-permissive licenses (MIT and Apache 2.0).
+
+For more details, see the [technical report](https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf).
+
+## Serving with vLLM
+
+The model can be served on 2x H200s:
+```bash
+vllm serve PrimeIntellect/INTELLECT-3.1 \
+    --tensor-parallel-size 2 \
+    --enable-auto-tool-choice \
+    --tool-call-parser qwen3_coder \
+    --reasoning-parser deepseek_r1
+```
+
+## Citation
+
+```bibtex
+@misc{intellect3.1,
+  title={INTELLECT-3.1: Technical Report},
+  author={Prime Intellect Team},
+  year={2025},
+  url={https://huggingface.co/PrimeIntellect/INTELLECT-3.1}
+}
+```

chat_template.jinja

@@ -0,0 +1,137 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are INTELLECT-4, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string %}
+            {%- if message.reasoning_content is defined  -%}
+                {%- if message.reasoning_content -%}
+                    {{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
+                {%- else -%}
+                    {{ '\n<think></think>' }}
+                {%- endif -%}
+            {%- endif -%}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.role == "assistant" and message.reasoning_content is defined %}
+            {%- if message.reasoning_content -%}
+                {{ '\n<think>' + message.reasoning_content.strip() + '</think>' }}
+            {%- else -%}
+                {{ '\n<think></think>' }}
+            {%- endif -%}
+            {%- if message.content.strip() -%}
+                {{ '\n' + message.content.strip() }}
+            {%- endif -%}
+        {%- else %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {{- '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n<think>' }}
+{%- endif %}

config.json

@@ -0,0 +1,227 @@
+{
+  "architectures": [
+    "Glm4MoeForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_glm4_moe.Glm4MoeConfig",
+    "AutoModel": "modeling_glm4_moe.Glm4MoeModel",
+    "AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM"
+  },
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    151334,
+    151329
+  ],
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 10944,
+  "max_position_embeddings": 131072,
+  "model_type": "glm4_moe",
+  "moe_intermediate_size": 1408,
+  "n_group": 1,
+  "n_routed_experts": 128,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 96,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 8,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "format": "pack-quantized",
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 32,
+          "num_bits": 8,
+          "observer": "mse",
+          "observer_kwargs": {},
+          "scale_dtype": null,
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int",
+          "zp_dtype": null
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": null,
+    "ignore": [
+      "model.layers.0.self_attn.q_proj",
+      "model.layers.0.self_attn.k_proj",
+      "model.layers.0.self_attn.v_proj",
+      "model.layers.0.self_attn.o_proj",
+      "model.layers.0.mlp.gate_proj",
+      "model.layers.0.mlp.up_proj",
+      "model.layers.0.mlp.down_proj",
+      "model.layers.1.mlp.shared_experts.gate_proj",
+      "model.layers.1.mlp.shared_experts.up_proj",
+      "model.layers.1.mlp.shared_experts.down_proj",
+      "model.layers.2.mlp.shared_experts.gate_proj",
+      "model.layers.2.mlp.shared_experts.up_proj",
+      "model.layers.2.mlp.shared_experts.down_proj",
+      "model.layers.3.mlp.shared_experts.gate_proj",
+      "model.layers.3.mlp.shared_experts.up_proj",
+      "model.layers.3.mlp.shared_experts.down_proj",
+      "model.layers.4.mlp.shared_experts.gate_proj",
+      "model.layers.4.mlp.shared_experts.up_proj",
+      "model.layers.4.mlp.shared_experts.down_proj",
+      "model.layers.5.mlp.shared_experts.gate_proj",
+      "model.layers.5.mlp.shared_experts.up_proj",
+      "model.layers.5.mlp.shared_experts.down_proj",
+      "model.layers.6.mlp.shared_experts.gate_proj",
+      "model.layers.6.mlp.shared_experts.up_proj",
+      "model.layers.6.mlp.shared_experts.down_proj",
+      "model.layers.7.mlp.shared_experts.gate_proj",
+      "model.layers.7.mlp.shared_experts.up_proj",
+      "model.layers.7.mlp.shared_experts.down_proj",
+      "model.layers.8.mlp.shared_experts.gate_proj",
+      "model.layers.8.mlp.shared_experts.up_proj",
+      "model.layers.8.mlp.shared_experts.down_proj",
+      "model.layers.9.mlp.shared_experts.gate_proj",
+      "model.layers.9.mlp.shared_experts.up_proj",
+      "model.layers.9.mlp.shared_experts.down_proj",
+      "model.layers.10.mlp.shared_experts.gate_proj",
+      "model.layers.10.mlp.shared_experts.up_proj",
+      "model.layers.10.mlp.shared_experts.down_proj",
+      "model.layers.11.mlp.shared_experts.gate_proj",
+      "model.layers.11.mlp.shared_experts.up_proj",
+      "model.layers.11.mlp.shared_experts.down_proj",
+      "model.layers.12.mlp.shared_experts.gate_proj",
+      "model.layers.12.mlp.shared_experts.up_proj",
+      "model.layers.12.mlp.shared_experts.down_proj",
+      "model.layers.13.mlp.shared_experts.gate_proj",
+      "model.layers.13.mlp.shared_experts.up_proj",
+      "model.layers.13.mlp.shared_experts.down_proj",
+      "model.layers.14.mlp.shared_experts.gate_proj",
+      "model.layers.14.mlp.shared_experts.up_proj",
+      "model.layers.14.mlp.shared_experts.down_proj",
+      "model.layers.15.mlp.shared_experts.gate_proj",
+      "model.layers.15.mlp.shared_experts.up_proj",
+      "model.layers.15.mlp.shared_experts.down_proj",
+      "model.layers.16.mlp.shared_experts.gate_proj",
+      "model.layers.16.mlp.shared_experts.up_proj",
+      "model.layers.16.mlp.shared_experts.down_proj",
+      "model.layers.17.mlp.shared_experts.gate_proj",
+      "model.layers.17.mlp.shared_experts.up_proj",
+      "model.layers.17.mlp.shared_experts.down_proj",
+      "model.layers.18.mlp.shared_experts.gate_proj",
+      "model.layers.18.mlp.shared_experts.up_proj",
+      "model.layers.18.mlp.shared_experts.down_proj",
+      "model.layers.19.mlp.shared_experts.gate_proj",
+      "model.layers.19.mlp.shared_experts.up_proj",
+      "model.layers.19.mlp.shared_experts.down_proj",
+      "model.layers.20.mlp.shared_experts.gate_proj",
+      "model.layers.20.mlp.shared_experts.up_proj",
+      "model.layers.20.mlp.shared_experts.down_proj",
+      "model.layers.21.mlp.shared_experts.gate_proj",
+      "model.layers.21.mlp.shared_experts.up_proj",
+      "model.layers.21.mlp.shared_experts.down_proj",
+      "model.layers.22.mlp.shared_experts.gate_proj",
+      "model.layers.22.mlp.shared_experts.up_proj",
+      "model.layers.22.mlp.shared_experts.down_proj",
+      "model.layers.23.mlp.shared_experts.gate_proj",
+      "model.layers.23.mlp.shared_experts.up_proj",
+      "model.layers.23.mlp.shared_experts.down_proj",
+      "model.layers.24.mlp.shared_experts.gate_proj",
+      "model.layers.24.mlp.shared_experts.up_proj",
+      "model.layers.24.mlp.shared_experts.down_proj",
+      "model.layers.25.mlp.shared_experts.gate_proj",
+      "model.layers.25.mlp.shared_experts.up_proj",
+      "model.layers.25.mlp.shared_experts.down_proj",
+      "model.layers.26.mlp.shared_experts.gate_proj",
+      "model.layers.26.mlp.shared_experts.up_proj",
+      "model.layers.26.mlp.shared_experts.down_proj",
+      "model.layers.27.mlp.shared_experts.gate_proj",
+      "model.layers.27.mlp.shared_experts.up_proj",
+      "model.layers.27.mlp.shared_experts.down_proj",
+      "model.layers.28.mlp.shared_experts.gate_proj",
+      "model.layers.28.mlp.shared_experts.up_proj",
+      "model.layers.28.mlp.shared_experts.down_proj",
+      "model.layers.29.mlp.shared_experts.gate_proj",
+      "model.layers.29.mlp.shared_experts.up_proj",
+      "model.layers.29.mlp.shared_experts.down_proj",
+      "model.layers.30.mlp.shared_experts.gate_proj",
+      "model.layers.30.mlp.shared_experts.up_proj",
+      "model.layers.30.mlp.shared_experts.down_proj",
+      "model.layers.31.mlp.shared_experts.gate_proj",
+      "model.layers.31.mlp.shared_experts.up_proj",
+      "model.layers.31.mlp.shared_experts.down_proj",
+      "model.layers.32.mlp.shared_experts.gate_proj",
+      "model.layers.32.mlp.shared_experts.up_proj",
+      "model.layers.32.mlp.shared_experts.down_proj",
+      "model.layers.33.mlp.shared_experts.gate_proj",
+      "model.layers.33.mlp.shared_experts.up_proj",
+      "model.layers.33.mlp.shared_experts.down_proj",
+      "model.layers.34.mlp.shared_experts.gate_proj",
+      "model.layers.34.mlp.shared_experts.up_proj",
+      "model.layers.34.mlp.shared_experts.down_proj",
+      "model.layers.35.mlp.shared_experts.gate_proj",
+      "model.layers.35.mlp.shared_experts.up_proj",
+      "model.layers.35.mlp.shared_experts.down_proj",
+      "model.layers.36.mlp.shared_experts.gate_proj",
+      "model.layers.36.mlp.shared_experts.up_proj",
+      "model.layers.36.mlp.shared_experts.down_proj",
+      "model.layers.37.mlp.shared_experts.gate_proj",
+      "model.layers.37.mlp.shared_experts.up_proj",
+      "model.layers.37.mlp.shared_experts.down_proj",
+      "model.layers.38.mlp.shared_experts.gate_proj",
+      "model.layers.38.mlp.shared_experts.up_proj",
+      "model.layers.38.mlp.shared_experts.down_proj",
+      "model.layers.39.mlp.shared_experts.gate_proj",
+      "model.layers.39.mlp.shared_experts.up_proj",
+      "model.layers.39.mlp.shared_experts.down_proj",
+      "model.layers.40.mlp.shared_experts.gate_proj",
+      "model.layers.40.mlp.shared_experts.up_proj",
+      "model.layers.40.mlp.shared_experts.down_proj",
+      "model.layers.41.mlp.shared_experts.gate_proj",
+      "model.layers.41.mlp.shared_experts.up_proj",
+      "model.layers.41.mlp.shared_experts.down_proj",
+      "model.layers.42.mlp.shared_experts.gate_proj",
+      "model.layers.42.mlp.shared_experts.up_proj",
+      "model.layers.42.mlp.shared_experts.down_proj",
+      "model.layers.43.mlp.shared_experts.gate_proj",
+      "model.layers.43.mlp.shared_experts.up_proj",
+      "model.layers.43.mlp.shared_experts.down_proj",
+      "model.layers.44.mlp.shared_experts.gate_proj",
+      "model.layers.44.mlp.shared_experts.up_proj",
+      "model.layers.44.mlp.shared_experts.down_proj",
+      "model.layers.45.mlp.shared_experts.gate_proj",
+      "model.layers.45.mlp.shared_experts.up_proj",
+      "model.layers.45.mlp.shared_experts.down_proj",
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {},
+    "transform_config": {},
+    "version": "0.13.1.a20260218"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "routed_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_grouped_mm": true,
+  "use_qk_norm": false,
+  "vocab_size": 151552
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [
+    151334,
+    151329
+  ],
+  "pad_token_id": 151329,
+  "transformers_version": "4.56.1",
+  "use_cache": false
+}

model-00001-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f6fea5aff67c0e4fc96c3462ae28d8d4bf06c3e3a9e0ded396999828e4d4cc
+size 4998809472

model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3df9f4810588d89a4a583b5160f640e06ef05bb801e3e931a8ea1a566d6451
+size 4997183232

model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb733a4f4874718497774dd697ba253592b224d4d94f00c5deff7e06e0a79256
+size 4997183232

model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3838d82f0052650a548e3c5664aa79e4291d42bb50ab91b58fbd077d4caee741
+size 4997183232

model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7b388dc233fa9bbbc55dc241d3bc9810bfe175222b582cad149aac88fb80d1
+size 4997183568

model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f3d86274d5b6aeab08e893f6a6ab4a2e09c2590b9dc328e4651ae60aaa5752b
+size 4997185576

model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70fa0573e210900d4324362cebf91abbae418e985d39b1002c4c325031ee8dc
+size 4997185576

model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdca32449a1d09f5812068fdde75bdc0598021eaeb762e19bb6f10da4a0393b4
+size 4997185576

model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30902aa0405b0a59adc8244fe5b19e9e202421a6ef9e96c5f1b752500ff0c2db
+size 4997185576

model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8266ef2f78007f9866477c7e0553d9b3763e3d1203681fb06de62361c4191d72
+size 4997185576

model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b121bcb7d2d00ee9c0185358028b18420db2636aaf2472a0a041450dbe8d6c45
+size 4997185576

model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cdfdfb20e99562aff7477b5f139dc8caca4d3b16397c46101405f2bbcd0165
+size 4997185576

model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323ddaa65517daa6e453afc69cd8e0f284132340a38febfe3617567efcaf23c6
+size 4997185576

model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84deb8248ab49354c59785d2fb19296fcd1a2b273fd8bd65f9bb72a71757186f
+size 4997185576

model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5588ae8d793e3d090308592fb961c20661f655ffbc7788da7d3b67fffdea952
+size 4997185576

model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84fbbf66ac47323212f5fcbe39627967fd1c76bb76f6a44d6ac57a5b8926e141
+size 4997185576

model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2baf92fed37c2ce3f1c32ba5b761ee040c2652ddc11e479a3f865224de5bdb
+size 4997185576

model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0de2d3832e8b03ca2bc214c2ca280b2278cce61abdcf1b69072a4f9a09c56275
+size 4997185576

model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0c2474b3e8e58715e9345dca19f814a9f71ed44800e1035ab30014971a9101
+size 4997185576

model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36af82dba578cd53455f9ae19ed873783c7436b00df220437d25f5cd656d10f
+size 4997185576

model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54060618fa95512cb331f687b85e1957e4a8f3be39d1647ae7a7af08fb1adde3
+size 4997185576

model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a726cd96cd09c5ce168a9078b4211f746becd420c399ee837c4ac3b35eb35776
+size 4997185576

model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80707ef1cff21efc62b8b96215cbbdb5ab6d9125184e5c3b4c462cc538ba8ed1
+size 4501359360

model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b492ff00be67d1d9e7cda527fa45288c99609e108e32388acd985518a2b0058
+size 1241514112

recipe.yaml

@@ -0,0 +1,41 @@
+default_stage:
+  default_modifiers:
+    AWQModifier:
+      config_groups:
+        group_0:
+          targets: [Linear]
+          weights:
+            num_bits: 8
+            type: int
+            symmetric: true
+            group_size: 32
+            strategy: group
+            block_structure: null
+            dynamic: false
+            actorder: null
+            scale_dtype: null
+            zp_dtype: null
+            observer: mse
+            observer_kwargs: {}
+          input_activations: null
+          output_activations: null
+          format: null
+      targets: [Linear]
+      ignore: [model.embed_tokens, 're:model[.]layers[.]0[.].*', 're:.*shared_experts.*',
+        're:.*mlp[.]gate$', model.norm, lm_head]
+      mappings:
+      - smooth_layer: re:.*layers[.]([1-9]\d*)[.]input_layernorm$
+        balance_layers: ['re:.*layers[.]([1-9]\d*)[.].*q_proj$', 're:.*layers[.]([1-9]\d*)[.].*k_proj$',
+          're:.*layers[.]([1-9]\d*)[.].*v_proj$']
+        activation_hook_target: null
+      - smooth_layer: re:.*layers[.]([1-9]\d*)[.]post_attention_layernorm$
+        balance_layers: ['re:.*layers[.]([1-9]\d*)[.]mlp[.]experts[.]\d+[.]gate_proj$', 're:.*layers[.]([1-9]\d*)[.]mlp[.]experts[.]\d+[.]up_proj$',
+          're:.*layers[.]([1-9]\d*)[.]mlp[.]shared_experts[.]gate_proj$', 're:.*layers[.]([1-9]\d*)[.]mlp[.]shared_experts[.]up_proj$',
+          're:.*layers[.]([1-9]\d*)[.]mlp[.]gate$']
+        activation_hook_target: null
+      - smooth_layer: re:.*layers[.]([1-9]\d*)[.]mlp[.]experts[.]\d+[.]up_proj$
+        balance_layers: ['re:.*layers[.]([1-9]\d*)[.]mlp[.]experts[.]\d+[.]down_proj$']
+        activation_hook_target: null
+      offload_device: !!python/object/apply:torch.device [cpu]
+      duo_scaling: true
+      n_grid: 20

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064
+size 19971076

tokenizer_config.json

@@ -0,0 +1,341 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151343": {
+      "content": "<|begin_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151344": {
+      "content": "<|end_of_audio|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151345": {
+      "content": "<|begin_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151346": {
+      "content": "<|end_of_transcription|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151347": {
+      "content": "<|code_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151348": {
+      "content": "<|code_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151349": {
+      "content": "<|code_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151350": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151351": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151352": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151353": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151354": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151355": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151356": {
+      "content": "<arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151357": {
+      "content": "</arg_key>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151358": {
+      "content": "<arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151359": {
+      "content": "</arg_value>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151360": {
+      "content": "/nothink",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151361": {
+      "content": "<|begin_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151362": {
+      "content": "<|end_of_box|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151363": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151364": {
+      "content": "<|video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151365": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151366": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>",
+    "<|begin_of_audio|>",
+    "<|end_of_audio|>",
+    "<|begin_of_transcription|>",
+    "<|end_of_transcription|>",
+    "<|code_prefix|>",
+    "<|code_middle|>",
+    "<|code_suffix|>",
+    "/nothink"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 128000,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}