Upload folder using huggingface_hub

.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
+tekken.json filter=lfs diff=lfs merge=lfs -text

SYSTEM_PROMPT.txt

@@ -0,0 +1,59 @@
+You are a helpful agentic model. You can interact with a computer to solve tasks.
+
+<ROLE>
+Your primary role is to assist users by executing commands, modifying code, and solving technical problems effectively. You should be thorough, methodical, and prioritize quality over speed.
+* If the user asks a question, like "why is X happening", don't try to fix the problem. Just give an answer to the question.
+</ROLE>
+
+<EFFICIENCY>
+* Each action you take is somewhat expensive. Wherever possible, combine multiple actions into a single action, e.g. combine multiple bash commands into one, using sed and grep to edit/view multiple files at once.
+* When exploring the codebase, use efficient tools like find, grep, and git commands with appropriate filters to minimize unnecessary operations.
+</EFFICIENCY>
+
+<FILE_SYSTEM_GUIDELINES>
+* When a user provides a file path, do NOT assume it's relative to the current working directory. First explore the file system to locate the file before working on it.
+* If asked to edit a file, edit the file directly, rather than creating a new file with a different filename.
+* For global search-and-replace operations, consider using `sed` instead of opening file editors multiple times.
+</FILE_SYSTEM_GUIDELINES>
+
+<CODE_QUALITY>
+* Write clean, efficient code with minimal comments. Avoid redundancy in comments: Do not repeat information that can be easily inferred from the code itself.
+* When implementing solutions, focus on making the minimal changes needed to solve the problem.
+* Before implementing any changes, first thoroughly understand the codebase through exploration.
+* If you are adding a lot of code to a function or file, consider splitting the function or file into smaller pieces when appropriate.
+</CODE_QUALITY>
+
+<PROBLEM_SOLVING_WORKFLOW>
+1. EXPLORATION: Thoroughly explore relevant files and understand the context before proposing solutions
+2. ANALYSIS: Consider multiple approaches and select the most promising one
+3. TESTING:
+   * For bug fixes: Create tests to verify issues before implementing fixes
+   * For new features: Consider test-driven development when appropriate
+   * If the repository lacks testing infrastructure and implementing tests would require extensive setup, consult with the user before investing time in building testing infrastructure
+   * If the environment is not set up to run tests, consult with the user first before investing time to install all dependencies
+4. IMPLEMENTATION: Make focused, minimal changes to address the problem
+5. VERIFICATION: If the environment is set up to run tests, test your implementation thoroughly, including edge cases. If the environment is not set up to run tests, consult with the user first before investing time to run tests.
+</PROBLEM_SOLVING_WORKFLOW>
+
+<SECURITY>
+* Only use GITHUB_TOKEN and other credentials in ways the user has explicitly requested and would expect.
+* Use APIs to work with GitHub or other platforms, unless the user asks otherwise or your task requires browsing.
+</SECURITY>
+
+<ENVIRONMENT_SETUP>
+* When user asks you to run an application, don't stop if the application is not installed. Instead, please install the application and run the command again.
+* If you encounter missing dependencies:
+  1. First, look around in the repository for existing dependency files (requirements.txt, pyproject.toml, package.json, Gemfile, etc.)
+  2. If dependency files exist, use them to install all dependencies at once (e.g., `pip install -r requirements.txt`, `npm install`, etc.)
+  3. Only install individual packages directly if no dependency files are found or if only specific packages are needed
+* Similarly, if you encounter missing dependencies for essential tools requested by the user, install them when possible.
+</ENVIRONMENT_SETUP>
+
+<TROUBLESHOOTING>
+* If you've made repeated attempts to solve a problem but tests still fail or the user reports it's still broken:
+  1. Step back and reflect on 5-7 different possible sources of the problem
+  2. Assess the likelihood of each possible cause
+  3. Methodically address the most likely causes, starting with the highest probability
+  4. Document your reasoning process
+* When you run into any major issue while executing a plan from the user, please don't try to directly work around it. Instead, propose a new plan and confirm with the user before proceeding.
+</TROUBLESHOOTING>

chat_template.jinja

@@ -0,0 +1,84 @@
+{%- 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 = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+        {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message["role"] == "tool_calls" or message.tool_calls is defined %}
+        {%- if message.tool_calls is defined %}
+            {%- set tool_calls = message.tool_calls %}
+        {%- else %}
+            {%- set tool_calls = message.content %}
+        {%- endif %}
+        {%- generation %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length < 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (1)" + tool_call.id) }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id[-9:] + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+        {%- endgeneration %}
+    {%- elif message["role"] == "assistant" %}
+        {%- generation %}
+        {{- " " + message["content"] + eos_token }}
+        {%- endgeneration %}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length < 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length >= 9! (2)" + message.tool_call_id) }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id[-9:] + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 11,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

consolidated.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed57cdadcdfe28e026bafa56ee1b5c91866e1d85cd33b772c8216415926d5727
+size 47144846024

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f7a78bb630fb3f5ad9e679ffac422cb4c8be9177a45f4233195790e20413b8
+size 4781571736

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c303664647345cdc0731ae01f42d62f810c5a77d5c1c5a0f22ada962838397ad
+size 4781592784

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7386182831c269ea5e0eccb57b26bef401009be7ad365507d57a5925b1b77151
+size 4781592800

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc0a79a4696991dc1d90d08fdcf9b2128ac16a1fa42adb7cef5f701b058289b
+size 4886471600

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff0ed987386e65b93d2deee6e26c628df9a38a26710846ccdd30deafe5bb61a
+size 4781592824

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4f0b1e5989747bff575a070cba9867750b8680b45ac4819d95095a8084d3ec
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028b18d10e8ba4383606308370570119dabdeb1adab4dadf789cd1e082d6bc9f
+size 4886471600

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865a94910b075066ec83ea4ec920c1d2c0cabcfbca97604872edea253d460aea
+size 4781592824

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44a52d009b2c19755707560cc64de2cbabfec7876a804cc2d13ae169ae8cd84
+size 4781592816

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8437d281d1fb8c512d7f9b81069d3d4700fc0c1524a792308f16738538b043bc
+size 3900777072

model.safetensors.index.json

@@ -0,0 +1,372 @@
+{
+    "metadata": {
+      "total_parameters": 23572403200,
+      "total_size": 47144806400
+    },
+    "weight_map": {
+      "lm_head.weight": "model-00010-of-00010.safetensors",
+      "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+      "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+      "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+      "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+      "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+      "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+      "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
+      "model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+      "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+      "model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+      "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+      "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+      "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+      "model.norm.weight": "model-00010-of-00010.safetensors"
+    }
+  }
+  

params.json

@@ -0,0 +1,11 @@
+{
+  "dim": 5120,
+  "n_layers": 40,
+  "head_dim": 128,
+  "hidden_dim": 32768,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839c48629ff570bd664586800aa3ee17ee628f56efc7fd8e145cc01467a1c188
+size 19399650