初始化项目，由ModelHub XC社区提供模型

Model: mlx-community/rnj-1-instruct-bfloat16
Source: Original Platform

.gitattributes

@@ -0,0 +1,53 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+library_name: mlx
+tags:
+- mlx
+pipeline_tag: text-generation
+base_model: EssentialAI/rnj-1-instruct
+---
+
+# mlx-community/rnj-1-instruct-bfloat16
+
+This model [mlx-community/rnj-1-instruct-bfloat16](https://huggingface.co/mlx-community/rnj-1-instruct-bfloat16) was
+converted to MLX format from [EssentialAI/rnj-1-instruct](https://huggingface.co/EssentialAI/rnj-1-instruct)
+using mlx-lm version **0.28.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/rnj-1-instruct-bfloat16")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,122 @@
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) -%}
+{%- set emit = namespace(started=false) -%}
+
+{# ---------- Build base system message (always emitted) ---------- #}
+{%- set base_system = 'You are rnj-1, a foundation model trained by Essential AI.\n' -%}
+
+{# ---------- Optional tools preface as a synthetic system message ---------- #}
+{%- if tools %}
+  {%- set sys_preamble -%}
+# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>
+{%- for tool in tools %}
+{{ "\n" ~ (tool | tojson) }}
+{% endfor %}
+</tools>
+
+For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+<tool_call>
+{"name": <function-name>, "arguments": <args-json-object>}
+</tool_call>
+  {%- endset -%}
+
+  {# If the first user-provided message is system, include it above the tools preface #}
+  {%- set combined_system = (messages and messages[0].role == 'system')
+      and (messages[0].content is string) -%}
+  {%- set sys_content = (combined_system and (messages[0].content ~ "\n\n" ~ sys_preamble)) or sys_preamble -%}
+
+  {%- set content = '<|start_header_id|>system<|end_header_id|>\n' ~ base_system ~ '\n' ~ sys_content ~ '<|eot_id|>' -%}
+  {%- if not emit.started -%}{%- set content = bos_token ~ content -%}{%- set emit.started = true -%}{%- endif -%}
+  {{- content -}}
+{%- else %}
+  {# No tools: always emit base_system, and include user's system message if present #}
+  {%- set user_system_content = '' -%}
+  {%- if messages and messages[0].role == 'system' and (messages[0].content is string) -%}
+    {%- set user_system_content = '\n' ~ messages[0].content -%}
+  {%- endif -%}
+  {%- set content = '<|start_header_id|>system<|end_header_id|>\n' ~ base_system ~ user_system_content ~ '<|eot_id|>' -%}
+  {%- if not emit.started -%}{%- set content = bos_token ~ content -%}{%- set emit.started = true -%}{%- endif -%}
+  {{- content -}}
+{%- endif -%}
+
+{# ---------- Locate last user query for multi-step tool behavior ---------- #}
+{%- for message in messages[::-1] %}
+  {%- set index = (messages|length - 1) - loop.index0 -%}
+  {%- if ns.multi_step_tool
+        and message.role == "user"
+        and message.content is string
+        and not (message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) -%}
+    {%- set ns.multi_step_tool = false -%}
+    {%- set ns.last_query_index = index -%}
+  {%- endif -%}
+{%- endfor -%}
+
+{# ---------- Walk all messages and emit in Llama-3 format ---------- #}
+{%- for message in messages %}
+  {# normalize content #}
+  {%- if message.content is string -%}
+    {%- set content = message.content -%}
+  {%- else -%}
+    {%- set content = '' -%}
+  {%- endif -%}
+
+  {# --- user/system (non-initial system already handled above) --- #}
+  {%- if (message.role == "user") or (message.role == "system" and not loop.first) -%}
+    {%- set block = '<|start_header_id|>' ~ message.role ~ '<|end_header_id|>\n' ~ content ~ '<|eot_id|>' -%}
+    {%- if not emit.started -%}{%- set block = bos_token ~ block -%}{%- set emit.started = true -%}{%- endif -%}
+    {{- block -}}
+
+  {# --- assistant --- #}
+  {%- elif message.role == "assistant" -%}
+  
+    {%- set body = content -%}
+    {%- set header = '<|start_header_id|>assistant<|end_header_id|>\n' -%}
+    {%- if not emit.started -%}{{ bos_token }}{%- set emit.started = true -%}{%- endif -%}
+    {{- header -}}
+    {% generation %}
+    {{- body -}}
+    {%- if message.tool_calls -%}
+      {%- for tool_call in message.tool_calls -%}
+        {%- if tool_call.function -%}{%- set tc = tool_call.function -%}{%- else -%}{%- set tc = tool_call -%}{%- endif -%}
+        {%- set args_json = (tc.arguments if (tc.arguments is string) else (tc.arguments | tojson)) -%}
+        {%- if loop.first -%}
+          {{- '<tool_call>\n{"name": "' ~ tc.name ~ '", "arguments": ' ~ args_json ~ '}\n</tool_call>' -}}
+        {%- else -%}
+          {{- '\n<tool_call>\n{"name": "' ~ tc.name ~ '", "arguments": ' ~ args_json ~ '}\n</tool_call>' -}}
+        {%- endif -%}
+      {%- endfor -%}
+    {%- endif -%}
+    {{- '<|eot_id|>' -}}{%- endgeneration -%}
+  {# --- tool messages are wrapped as synthetic user messages with <tool_response> --- #}
+  {%- elif message.role == "tool" -%}
+    {%- set open_user = (loop.first or (loop.index0 > 0 and messages[loop.index0 - 1].role != "tool")) -%}
+    {%- set close_user = (loop.last or (loop.index0 < messages|length - 1 and messages[loop.index0 + 1].role != "tool")) -%}
+
+    {%- if open_user -%}
+      {%- set header = '<|start_header_id|>user<|end_header_id|>\n' -%}
+      {%- if not emit.started -%}{%- set header = bos_token ~ header -%}{%- set emit.started = true -%}{%- endif -%}
+      {{- header -}}
+    {%- endif -%}
+    {%- if open_user -%}
+      {{- '<tool_response>\n' -}}
+    {%- else -%}
+      {{- '\n<tool_response>\n' -}}
+    {%- endif -%}
+    {{- content -}}
+    {{- '\n</tool_response>' -}}
+
+    {%- if close_user -%}
+      {{- '<|eot_id|>' -}}
+    {%- endif -%}
+  {%- endif -%}
+{%- endfor -%}
+
+{# ---------- Add generation prompt header for the model to continue ---------- #}
+{%- if add_generation_prompt -%}
+  {%- set tail = '<|start_header_id|>assistant<|end_header_id|>\n' -%}
+  {{- tail -}}
+{%- endif -%}

config.json

@@ -0,0 +1,77 @@
+{
+    "architectures": [
+        "Gemma3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": null,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "head_dim": 128,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "layer_type": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 32768,
+    "model_type": "gemma3_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "query_pre_attn_scalar": 128,
+    "rms_norm_eps": 1e-06,
+    "rope_local_base_freq": 10000,
+    "rope_scaling": {
+        "attn_factor": 1.0,
+        "beta_fast": 64.0,
+        "beta_slow": 1.0,
+        "extrapolation_factor": 1.0,
+        "factor": 4.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "yarn"
+    },
+    "rope_theta": 10000,
+    "sliding_window": 32768,
+    "sliding_window_pattern": 1,
+    "torch_dtype": "float32",
+    "transformers_version": "4.51.2",
+    "use_cache": true,
+    "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 128009,
+  "pad_token_id": 128001,
+  "temperature": 0.2,
+  "do_sample": true,
+  "transformers_version": "4.51.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b77a0f5d24812004c9578c7d8b02e1360d4e56ad1abfd489a2e363e202a306be
+size 5295588590

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c2f0401c2b1df22654d38b96030f95d007d66606e6d19bf0ad3fac111e6fe3
+size 5352314644

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2f07fdec1d826c1fd7c392476b8dce071ac1700d03d2d07ed301e6dffafac2
+size 5352314632

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd03b880b0268f0edd9acdc0dda33fa6313b1e7a5f28b0c7f2b5acf7e26ecfa
+size 620833404

model.safetensors.index.json

@@ -0,0 +1,426 @@
+{
+    "metadata": {
+        "total_size": 16621002752,
+        "total_parameters": 8310501376
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.norm.weight": "model-00004-of-00004.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a2db531b75969ce3aeaaf126eb7957f7e07a28c7e770705787ef035f19d9da
+size 17209795