Nanbeige4.2-3B looped-transformer bundle (JANG)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,110 @@
+---
+language:
+- en
+- zh
+library_name: mlx
+license: apache-2.0
+base_model: Nanbeige/Nanbeige4.2-3B
+pipeline_tag: text-generation
+tags:
+- mlx
+- jang
+- mxfp8
+- quantized
+- apple-silicon
+- nanbeige
+- looped-transformer
+- reasoning
+- osaurus
+---
+
+<p align="center"><a href="https://osaurus.ai"><img src="./osaurus-x-banner.png" alt="Osaurus AI"></a></p>
+
+# OsaurusAI/Nanbeige4.2-3B-MXFP8
+
+MXFP8 build of [Nanbeige/Nanbeige4.2-3B](https://huggingface.co/Nanbeige/Nanbeige4.2-3B) — a 4.17B-parameter **Looped Transformer** reasoning model (en + zh, 256K context), quantized for Apple Silicon with uniform MXFP8 (e4m3) weights. This is format coverage — see the fidelity table before choosing it.
+
+> ### ⚠️ This architecture needs a loader that knows about the loop
+>
+> `num_loops = 2`: the same 22 decoder layers run **twice** over shared weights,
+> for an effective depth of 44. Two consequences a generic loader gets wrong:
+>
+> - **The KV cache has 44 slots, not 22** (slot = `layer_idx + loop_idx * num_hidden_layers`).
+>   A 22-slot cache does not crash — it emits fluent, confident, **wrong** tokens
+>   from the first one. This is verified with a negative control, not theory.
+> - **The final norm runs at the end of every loop**, not once at the end
+>   (`skip_loop_final_norm = false`). Loop 0's normed output is loop 1's input.
+>
+> `mlx_lm` 0.31.x has no `nanbeige` model class, so `mlx_lm.generate` alone will
+> not load this bundle. Use a runtime that implements the loop (see **Usage**).
+
+## Bundle
+
+| Field | Value |
+|---|---|
+| Source | `Nanbeige/Nanbeige4.2-3B` @ `fab06df` (Apache-2.0) |
+| Architecture | `nanbeige` — 22 layers × 2 loops (effective depth 44), 4.17B params, 256K ctx |
+| On-disk size | 4.0 GB (1 shard) |
+| Quantization | uniform 8-bit MX, no per-module overrides, group size 32 |
+| Norms, router bias | fp16 passthrough — plain Llama RMSNorm, **no +1 shift** |
+| Attention | 48 heads / 8 KV heads (GQA), `head_dim` 128 — note `n_heads × head_dim` (6144) ≠ `hidden_size` (3072) |
+| RoPE | θ = 7e7, NeoX half-rotation, full 128 dims, no scaling |
+| Modality | text-only (verified from the tensor index) |
+
+## Measured (M5 Max, 4-turn gate with a persistent 44-slot cache)
+
+| Metric | Thinking on | Thinking off |
+|---|---|---|
+| Decode | 34.6 tok/s | 27.9 tok/s |
+| Peak memory | 5.3 GB | 4.5 GB |
+
+Fidelity vs the bf16 source (5-prompt logit sweep): top-1 agreement **4/5**, mean KL **0.1446**, max KL 0.6844.
+
+## Profile comparison
+
+| Bundle | Size | Top-1 agreement vs bf16 | Mean KL | Max KL | Decode (thinking) |
+|---|---|---|---|---|---|
+| [`Nanbeige4.2-3B-JANG_6M`](https://huggingface.co/OsaurusAI/Nanbeige4.2-3B-JANG_6M) | 3.6 GB | **5/5** | **0.0010** | **0.0030** | 29.3 tok/s |
+| [`Nanbeige4.2-3B-JANG_4M`](https://huggingface.co/OsaurusAI/Nanbeige4.2-3B-JANG_4M) | 2.9 GB | 5/5 | 0.0192 | 0.0398 | **44.7 tok/s** |
+| [`Nanbeige4.2-3B-MXFP8`](https://huggingface.co/OsaurusAI/Nanbeige4.2-3B-MXFP8) | 4.0 GB | 4/5 | 0.1446 | 0.6844 | 34.6 tok/s |
+
+**Both JANG affine profiles beat MXFP8 on fidelity while being smaller** — the
+opposite of what the bit counts suggest. MXFP8's e4m3 elements carry ~3 mantissa
+bits each, so "8-bit MX" is not strictly better than 6-bit or 4-bit affine with a
+per-group scale **and** bias on this weight distribution. It showed up in
+behaviour too: in the multi-turn gate MXFP8 dated Tokyo's capital move to 1936,
+where both JANG builds said 1868.
+
+## Chat / reasoning
+
+- **Thinking is ON by default.** The generation prompt ends with an *open* `<think>\n`; only `enable_thinking=False` prefills a closed `<think>\n\n</think>\n\n`.
+- `preserve_thinking` controls whether previous turns' reasoning is kept. The template's default is to preserve; the vendor recommends `False` for general chat and `True` for multi-turn tool use and code-agent workflows.
+- Tool calls default to `tool_call_format="xml"` (the vendor's recommended format); `json` is supported for compatibility.
+- **Double-BOS trap:** the chat template already emits `<|im_start|>` (id 166100 = `bos_token`) and the tokenizer's post-processor prepends another. Tokenize the rendered template with `add_special_tokens=False`.
+- Stop token `eos_token_id = 166101` (`<|im_end|>`).
+- Sampling defaults (vendor `generation_config.json`, matching the model card): `temperature 0.6`, `top_p 0.95`, `top_k 20`. The vendor suggests `temperature 1.0` for agentic and tool-use tasks. The same values are stamped in `jang_config.chat.sampling_defaults`, and the two files are checked against each other at build time.
+
+## Usage
+
+The bundle is standard MLX safetensors with a per-module `{bits, group_size, mode}` map in `config.json[quantization]` — any loader must honor those overrides. It needs the `nanbeige` looped model class, which registers into `mlx_lm`:
+
+```python
+from jang_tools.nanbeige import mlx_register  # registers the looped nanbeige class
+from mlx_lm import load, generate
+from mlx_lm.sample_utils import make_sampler
+
+model, tok = load("OsaurusAI/Nanbeige4.2-3B-MXFP8")
+prompt = tok.apply_chat_template(
+    [{"role": "user", "content": "Which number is bigger, 9.11 or 9.8?"}],
+    add_generation_prompt=True, tokenize=False,
+)
+ids = tok.encode(prompt, add_special_tokens=False)  # template already emits BOS
+print(generate(model, tok, prompt=ids, max_tokens=1024,
+               sampler=make_sampler(temp=0.6, top_p=0.95, top_k=20)))
+```
+
+Osaurus and vMLX runtime support for the looped architecture is in progress; until it lands, use the path above.
+
+---
+
+Quantized and verified by **Jinho Jang** (eric@osaurus.ai). Base model © Nanbeige, Apache-2.0 (inherited).

added_tokens.json

@@ -0,0 +1,9 @@
+{
+  "</think>": 166104,
+  "</tool_call>": 166106,
+  "<think>": 166103,
+  "<tool_call>": 166105,
+  "<|endoftext|>": 166102,
+  "<|im_end|>": 166101,
+  "<|im_start|>": 166100
+}

chat_template.jinja

@@ -0,0 +1,195 @@
+
+
+{%- macro visible_text(content) -%}
+    {%- if content is string -%}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping -%}
+        {%- for item in content -%}
+            {%- if item is mapping and item.type == 'text' -%}
+                {{- item.text }}
+            {%- elif item is string -%}
+                {{- item }}
+            {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}
+                {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}
+                {{- "<reminder>You are unable to process this " ~ media_type ~ " because you don't have multi-modal input ability. Try different methods.</reminder>" }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{- content }}
+    {%- endif -%}
+{%- endmacro -%}
+
+
+{%- set tool_call_format = tool_call_format if tool_call_format is defined else 'xml' %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}    
+    {%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}
+        {{- visible_text(messages[0].content) + '\n\n' }}
+    {%- else %} 
+        {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。\n如果没有一个函数可以使用，请直接使用自然语言回复用户。\n如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。\n如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} 
+    {%- 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 %}
+    
+    {%- if tool_call_format == 'json' %}
+        {{- "\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 %}
+        {{- "\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n" }}
+        {{- '<tool_call>
+<function=example_function_name>
+<parameter=example_parameter_1>
+value_1
+</parameter>
+<parameter=example_parameter_2>
+This is the value for the second parameter
+that can span
+multiple lines
+</parameter>
+</function>
+</tool_call><|im_end|>\n' }}
+    {%- endif %}
+    
+{%- else %}
+    {%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}
+        {{- '<|im_start|>system\n' + visible_text(messages[0].content) + '<|im_end|>\n' }}
+    {%- else %} 
+        {{- '<|im_start|>system\n你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|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.get('role', '') == "user" and visible_text(message.content) is string and not(visible_text(message.content).startswith('<tool_response>') and visible_text(message.content).endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages %}
+    {%- if visible_text(message.content) is string %}
+        {%- set content = visible_text(message.content) %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    
+    {%- if message.get('role', '') == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+        
+    {%- elif message.get('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').rstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        
+        {%- if (preserve_thinking is defined and preserve_thinking is false) and (loop.index0 < ns.last_query_index) %}
+            {{- '<|im_start|>' + message.get('role', '') + '\n<think>\n\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.get('role', '') + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- endif %}
+        
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- if tool_call_format == 'json' %}
+                {%- 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 %}
+            {%- else %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    
+                    {%- if loop.first %}
+                        {%- if content|trim %}
+                            {{- '
+
+<tool_call>
+<function=' + tool_call.name + '>
+' }}
+                        {%- else %}
+                            {{- '<tool_call>
+<function=' + tool_call.name + '>
+' }}
+                        {%- endif %}
+                    {%- else %}
+                        {{- '
+<tool_call>
+<function=' + tool_call.name + '>
+' }}
+                    {%- endif %}
+                    
+                    {%- if tool_call.arguments is defined %}
+                        {%- for args_name, args_value in tool_call.arguments|items %}
+                            {{- '<parameter=' + args_name + '>
+' }}
+                            {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
+                            {{- args_value }}
+                            {{- '
+</parameter>
+' }}
+                        {%- endfor %}
+                    {%- endif %}
+                    {{- '</function>
+</tool_call>' }}
+                {%- endfor %}
+            {%- endif %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+        
+    {%- elif message.get('role', '') == "tool" %}
+        {%- if loop.previtem and loop.previtem.get('role', '') != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or loop.nextitem.get('role', '') != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- elif message.get('role', '') != '' %}
+        {{- '<|im_start|>' + message.get('role', '') + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>
+
+</think>
+
+' }}
+    {%- else %}
+        {{- '<think>
+' }}
+    {%- endif %}
+    
+{%- endif %}

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "NanbeigeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 166100,
+  "eos_token_id": 166101,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 10752,
+  "kv_channels": 128,
+  "loop_loss_weights": [],
+  "max_length": null,
+  "max_position_embeddings": 262144,
+  "model_type": "nanbeige",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 8,
+  "num_loops": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 70000000,
+  "skip_loop_final_norm": false,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 166144,
+  "weight_format": "mxfp8",
+  "quantization": {
+    "group_size": 32,
+    "bits": 8,
+    "mode": "mxfp8"
+  },
+  "jang_runtime": {
+    "architecture": "looped_transformer",
+    "cache_layout": "looped_kv_v1",
+    "num_loops": 2,
+    "num_hidden_layers": 22,
+    "cache_slots": 44,
+    "cache_slot_formula": "layer_idx + loop_idx * num_hidden_layers",
+    "loop_final_norm": "every_loop",
+    "shared_layer_weights_across_loops": true,
+    "position_ids_shared_across_loops": true,
+    "norm_convention": "llama_rmsnorm_no_plus_one",
+    "rope": {
+      "type": "neox_half_rotation",
+      "theta": 70000000,
+      "dims": 128,
+      "partial_rotary_factor": 1.0
+    },
+    "attention": {
+      "type": "gqa",
+      "n_heads": 48,
+      "n_kv_heads": 8,
+      "head_dim": 128,
+      "qkv_bias": false,
+      "qk_layernorm": false,
+      "n_heads_times_head_dim_equals_hidden": false
+    }
+  },
+  "capabilities": {
+    "reasoning_parser": "qwen3",
+    "tool_parser": "xml_function",
+    "think_in_template": true,
+    "supports_tools": true,
+    "supports_thinking": true,
+    "family": "nanbeige",
+    "modality": "text",
+    "modalities": {
+      "text": true,
+      "vision": false,
+      "audio": false,
+      "video": false
+    },
+    "has_vision": false,
+    "has_audio": false,
+    "has_video": false,
+    "cache_type": "kv"
+  }
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 166100,
+  "do_sample": true,
+  "eos_token_id": 166101,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.0"
+}

jang_config.json

@@ -0,0 +1,77 @@
+{
+  "version": 2,
+  "weight_format": "mxfp8",
+  "profile": "MXFP8",
+  "source_model": {
+    "name": "Nanbeige4.2-3B",
+    "architecture": "nanbeige"
+  },
+  "has_vision": false,
+  "has_audio": false,
+  "quantization": {
+    "method": "mxfp8",
+    "quantization_backend": "mx.quantize",
+    "mode": "mxfp8",
+    "group_size": 32,
+    "tier_bits": {
+      "attention": 8,
+      "mlp": 8,
+      "embed": 8
+    },
+    "norm_convention": "llama_rmsnorm_no_plus_one",
+    "per_module_override_count": 0,
+    "quantized_tensor_count": 156,
+    "passthrough_tensor_count": 45
+  },
+  "runtime": {
+    "architecture": "looped_transformer",
+    "num_loops": 2,
+    "cache_slots": 44,
+    "total_weight_bytes": 4300281408,
+    "total_weight_gb": 4.0
+  },
+  "capabilities": {
+    "reasoning_parser": "qwen3",
+    "tool_parser": "xml_function",
+    "think_in_template": true,
+    "supports_tools": true,
+    "supports_thinking": true,
+    "family": "nanbeige",
+    "modality": "text",
+    "modalities": {
+      "text": true,
+      "vision": false,
+      "audio": false,
+      "video": false
+    },
+    "has_vision": false,
+    "has_audio": false,
+    "has_video": false,
+    "cache_type": "kv"
+  },
+  "chat": {
+    "reasoning": {
+      "supported": true,
+      "parser": "qwen3",
+      "default_enabled": true,
+      "default_mode": "think",
+      "modes": [
+        "think",
+        "no_think"
+      ]
+    },
+    "tool_calling": {
+      "supported": true,
+      "parser": "xml_function",
+      "call_format": "xml"
+    },
+    "sampling_defaults": {
+      "temperature": 0.6,
+      "top_p": 0.95,
+      "top_k": 20
+    },
+    "template_kwargs_defaults": {
+      "enable_thinking": true
+    }
+  }
+}

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12ca3a1ac14b3f914ddee59e4d8f4e41023ae4603e188b7dabb4e8bbdb477cd
+size 4300281408

model.safetensors.index.json

@@ -0,0 +1,365 @@
+{
+  "metadata": {
+    "format": "mxfp8",
+    "total_size": 4300281408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00001.safetensors",
+    "lm_head.scales": "model-00001-of-00001.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
+    "model.embed_tokens.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00001.safetensors",
+    "model.norm.weight": "model-00001-of-00001.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d858a0fc007f22af6ae18bfa1ae52d30e398aa9cd1ea06e7777176869346a3f
+size 18450979

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb41d04798b714520a9b075727b0226538b7330254299062742c50ec8374bc36
+size 2782298

tokenizer_config.json

@@ -0,0 +1,103 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166100": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166101": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166102": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "166103": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166104": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166105": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166106": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "\n\n{%- macro visible_text(content) -%}\n    {%- if content is string -%}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping -%}\n        {%- for item in content -%}\n            {%- if item is mapping and item.type == 'text' -%}\n                {{- item.text }}\n            {%- elif item is string -%}\n                {{- item }}\n            {%- elif item is mapping and item.type in ['image', 'image_url', 'video', 'video_url', 'audio', 'audio_url', 'input_audio'] -%}\n                {%- set media_type = item.type | replace('_url', '') | replace('input_', '') -%}\n                {{- \"<reminder>You are unable to process this \" ~ media_type ~ \" because you don't have multi-modal input ability. Try different methods.</reminder>\" }}\n            {%- endif -%}\n        {%- endfor -%}\n    {%- else -%}\n        {{- content }}\n    {%- endif -%}\n{%- endmacro -%}\n\n\n{%- set tool_call_format = tool_call_format if tool_call_format is defined else 'xml' %}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}    \n    {%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}\n        {{- visible_text(messages[0].content) + '\\n\\n' }}\n    {%- else %} \n        {{- '你是一位工具函数调用专家，你会得到一个问题和一组可能的工具函数。根据问题，你需要进行一个或多个函数/工具调用以实现目的，请尽量尝试探索通过工具解决问题。\\n如果没有一个函数可以使用，请直接使用自然语言回复用户。\\n如果给定的问题缺少函数所需的参数，请使用自然语言进行提问，向用户询问必要信息。\\n如果调用结果已经足够回答用户问题，请对历史结果进行总结，使用自然语言回复用户。' }} \n    {%- endif %}\n\n    {{- \"# 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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    \n    {%- if tool_call_format == 'json' %}\n        {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n\" }}\n        {{- '<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n' }}\n    {%- else %}\n        {{- \"\\n</tools>\\n\\nFor each function call, output the function name and arguments within the following XML format:\\n\" }}\n        {{- '<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call><|im_end|>\\n' }}\n    {%- endif %}\n    \n{%- else %}\n    {%- if messages|length > 0 and messages[0].get('role', '') == 'system' %}\n        {{- '<|im_start|>system\\n' + visible_text(messages[0].content) + '<|im_end|>\\n' }}\n    {%- else %} \n        {{- '<|im_start|>system\\n你是南北阁，一款由BOSS直聘自主研发并训练的专业大语言模型。<|im_end|>\\n' }} \n    {%- endif %}\n{%- endif %}\n\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.get('role', '') == \"user\" and visible_text(message.content) is string and not(visible_text(message.content).startswith('<tool_response>') and visible_text(message.content).endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n\n{%- for message in messages %}\n    {%- if visible_text(message.content) is string %}\n        {%- set content = visible_text(message.content) %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    \n    {%- if message.get('role', '') == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n        \n    {%- elif message.get('role', '') == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n').rstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        \n        {%- if (preserve_thinking is defined and preserve_thinking is false) and (loop.index0 < ns.last_query_index) %}\n            {{- '<|im_start|>' + message.get('role', '') + '\\n<think>\\n\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.get('role', '') + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- endif %}\n        \n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- if tool_call_format == 'json' %}\n                {%- for tool_call in message.tool_calls %}\n                    {%- if (loop.first and content) or (not loop.first) %}\n                        {{- '\\n' }}\n                    {%- endif %}\n                    {%- if tool_call.function %}\n                        {%- set tool_call = tool_call.function %}\n                    {%- endif %}\n                    {{- '<tool_call>\\n{\"name\": \"' }}\n                    {{- tool_call.name }}\n                    {{- '\", \"arguments\": ' }}\n                    {%- if tool_call.arguments is string %}\n                        {{- tool_call.arguments }}\n                    {%- else %}\n                        {{- tool_call.arguments | tojson }}\n                    {%- endif %}\n                    {{- '}\\n</tool_call>' }}\n                {%- endfor %}\n            {%- else %}\n                {%- for tool_call in message.tool_calls %}\n                    {%- if tool_call.function is defined %}\n                        {%- set tool_call = tool_call.function %}\n                    {%- endif %}\n                    \n                    {%- if loop.first %}\n                        {%- if content|trim %}\n                            {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}\n                        {%- else %}\n                            {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}\n                        {%- endif %}\n                    {%- else %}\n                        {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}\n                    {%- endif %}\n                    \n                    {%- if tool_call.arguments is defined %}\n                        {%- for args_name, args_value in tool_call.arguments|items %}\n                            {{- '<parameter=' + args_name + '>\n' }}\n                            {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n                            {{- args_value }}\n                            {{- '\n</parameter>\n' }}\n                        {%- endfor %}\n                    {%- endif %}\n                    {{- '</function>\n</tool_call>' }}\n                {%- endfor %}\n            {%- endif %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n        \n    {%- elif message.get('role', '') == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.get('role', '') != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or loop.nextitem.get('role', '') != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- elif message.get('role', '') != '' %}\n        {{- '<|im_start|>' + message.get('role', '') + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- endif %}\n{%- endfor %}\n\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    \n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\n\n</think>\n\n' }}\n    {%- else %}\n        {{- '<think>\n' }}\n    {%- endif %}\n    \n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}