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

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 2560,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,198 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+- ru
+- es
+- fr
+- de
+- ar
+- nl
+- vi
+- hi
+- ko
+- ja
+- it
+- id
+- pt
+- pl
+- tr
+- da
+- th
+- sv
+- fa
+- uk
+- cs
+- 'no'
+- el
+- ca
+- ro
+- fi
+- bg
+- tl
+- gl
+- my
+- hy
+- km
+- ne
+- hu
+- eu
+- he
+- lo
+- sw
+- az
+- lv
+- si
+- sk
+- tg
+- et
+- lt
+- ms
+- hr
+- is
+- sl
+- sr
+- ur
+- bn
+- af
+- ta
+- ka
+- te
+- ml
+- mn
+- nn
+- kk
+- cy
+- mr
+- sq
+- nb
+- mk
+- jv
+- kn
+- eo
+- la
+- gu
+- uz
+- am
+- oc
+- be
+- mg
+- vo
+- pa
+- lb
+- ht
+- br
+- ga
+- xh
+- tt
+- bs
+- yo
+base_model:
+- codefuse-ai/F2LLM-v2-4B
+base_model_relation: quantized
+pipeline_tag: feature-extraction
+library_name: mlx
+tags:
+- mlx
+- mlx-embeddings
+- sentence-transformers
+- feature-extraction
+- qwen3
+datasets:
+- codefuse-ai/F2LLM-v2
+---
+# fcmeyer/F2LLM-v2-4B-mlx-6bit
+
+[codefuse-ai/F2LLM-v2-4B](https://huggingface.co/codefuse-ai/F2LLM-v2-4B) converted to native MLX format —
+**6-bit (affine, group size 64)**, 3.1 GB on disk.
+
+F2LLM-v2-4B is a 4B-parameter multilingual text embedding model from CodeFuse (Qwen3
+trunk, 2560-dimensional embeddings, last-token pooling with L2 normalization). All credit
+for the model belongs to the original authors; this repository only changes the weight
+format so the model runs natively on Apple Silicon through
+[mlx-embeddings](https://github.com/Blaizzy/mlx-embeddings).
+
+## Usage
+
+```bash
+pip install mlx-embeddings
+```
+
+```python
+from mlx_embeddings import load, generate
+import mlx.core as mx
+
+model, tokenizer = load("fcmeyer/F2LLM-v2-4B-mlx-6bit")
+
+# Queries get the instruction prompt; documents do not.
+query_prompt = "Instruct: Given a question, retrieve passages that can help answer the question.\nQuery: "
+query = "What is F2LLM used for?"
+documents = [
+    "We present F2LLM, a family of fully open embedding LLMs that achieve a strong balance between model size, training data, and embedding performance.",
+    "F2LLM is a model for computing text embeddings that can be used for various NLP tasks such as information retrieval, semantic search, and text classification.",
+    "F2LLM 是 CodeFuse 开源的系列嵌入模型。",
+    "F2LLM — это модель вычисления встраивания текста, которую можно использовать для различных задач НЛП, таких как поиск информации, семантический поиск и классификация текста."
+]
+
+# Pass max_length explicitly — generate() defaults to max_length=512 with
+# truncation enabled, which silently clips longer inputs.
+query_embedding = generate(model, tokenizer, texts=[query_prompt + query],
+                           max_length=8192).text_embeds
+document_embeddings = generate(model, tokenizer, texts=documents,
+                               max_length=8192).text_embeds
+
+similarity = query_embedding @ document_embeddings.T
+print(similarity)
+# [0.6326, 0.8613, 0.7245, 0.8386]
+```
+
+### Prompt format
+
+Custom instructions follow the base model's format:
+
+```text
+Instruct: your_instruction
+Query: your_query
+```
+
+For retrieval and reranking, prompt the queries and leave documents unprompted. For
+symmetric tasks (STS, clustering, bitext mining) the model works with or without prompts
+on both sides.
+
+## Conversion
+
+```bash
+pip install "mlx-embeddings @ git+https://github.com/Blaizzy/mlx-embeddings@9b28270be81211f2b8daed0041aec65ea5dc4b28"
+python -m mlx_embeddings.convert --hf-path codefuse-ai/F2LLM-v2-4B \
+    --mlx-path F2LLM-v2-4B-mlx-6bit --dtype bfloat16 -q --q-bits 6 --q-group-size 64
+```
+
+Converted with `mlx` 0.32.2 and `mlx-embeddings` 0.1.1
+(commit [`9b28270be812`](https://github.com/Blaizzy/mlx-embeddings/commit/9b28270be81211f2b8daed0041aec65ea5dc4b28)).
+
+All linear layers **and** the token embedding table are quantized to 6 bits with MLX affine quantization at group size 64. RMSNorm weights and the quantization scales/biases stay in bfloat16.
+
+## Accuracy check
+
+Each build was compared against a PyTorch bfloat16 reference run of the original
+checkpoint on the 5-string fixture from the base model card (one prompted English query
+plus four documents in English, Chinese, and Russian). Embeddings were re-normalized in
+float32 before comparison, since bfloat16 output leaves vectors slightly off unit norm.
+
+| Build | Size | Min cosine vs PyTorch | Max Δ on query→document similarity | Ranking preserved |
+|---|---|---|---|---|
+| `F2LLM-v2-4B-mlx-bf16` | 7.5 GB | 0.99984 | 0.0017 | yes |
+| `F2LLM-v2-4B-mlx-8bit` | 4.0 GB | 0.99954 | 0.0020 | yes |
+| `F2LLM-v2-4B-mlx-6bit` **(this repo)** | 3.1 GB | 0.99696 | 0.0078 | yes |
+
+The PyTorch reference itself reproduces the similarity row published on the base model
+card to within 0.005 (bfloat16 on CPU versus the card's bfloat16 on CUDA).
+
+This is a small smoke-test fixture, not a benchmark. No MTEB or retrieval evaluation was
+run on the quantized builds — if quantization loss matters for your task, measure it on
+your own data.
+
+## License
+
+Apache 2.0, inherited from [codefuse-ai/F2LLM-v2-4B](https://huggingface.co/codefuse-ai/F2LLM-v2-4B).

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- 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 %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,35 @@
+{
+    "architectures": [
+        "Qwen3Model"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 40960,
+    "max_window_layers": 36,
+    "model_type": "qwen3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 6,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.0",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+}

config_sentence_transformers.json

@@ -0,0 +1,8 @@
+{
+    "prompts": {
+      "query": "Instruct: Given a question, retrieve passages that can help answer the question.\nQuery: ",
+      "document": ""
+    },
+    "default_prompt_name": null,
+    "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455680a0a41101c2bb8c7172ac6d36e460056cfe5a18089c3db666219ad598f5
+size 3268590767

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 8044936192,
+    "mergekit_version": "0.1.4"
+  },
+  "weight_map": {
+    "embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

modules.json

@@ -0,0 +1,20 @@
+[
+    {
+      "idx": 0,
+      "name": "0",
+      "path": "",
+      "type": "sentence_transformers.models.Transformer"
+    },
+    {
+      "idx": 1,
+      "name": "1",
+      "path": "1_Pooling",
+      "type": "sentence_transformers.models.Pooling"
+    },
+    {
+      "idx": 2,
+      "name": "2",
+      "path": "2_Normalize",
+      "type": "sentence_transformers.models.Normalize"
+    }
+]

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d4dfb58cd7498c4651780628269e16f3ecb6d995edf2ce952b455093983d04
+size 11423191

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}