Text Generation
MLX
Safetensors
Korean
English
qwen3_moe
Mixture of Experts
pruning
reap
k-reap
korean
expert-pruning
conversational
Instructions to use KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX with MLX:
# Make sure mlx-lm is installed # pip install --upgrade mlx-lm # Generate text with mlx-lm from mlx_lm import load, generate model, tokenizer = load("KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX") prompt = "Write a story about Einstein" messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) text = generate(model, tokenizer, prompt=prompt, verbose=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX
Run Hermes
hermes
- OpenClaw new
How to use KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- MLX LM
How to use KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX", "messages": [ {"role": "user", "content": "Hello"} ] }'
Add files using upload-large-folder tool
Browse files- README.md +87 -0
- chat_template.jinja +117 -0
- config.json +38 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model-00008-of-00016.safetensors +3 -0
- model-00009-of-00016.safetensors +3 -0
- model-00010-of-00016.safetensors +3 -0
- model-00011-of-00016.safetensors +3 -0
- model-00012-of-00016.safetensors +3 -0
- model-00013-of-00016.safetensors +3 -0
- model-00014-of-00016.safetensors +3 -0
- model-00015-of-00016.safetensors +3 -0
- model-00016-of-00016.safetensors +3 -0
- model.safetensors.index.json +0 -0
- tensor_hash_validation.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
|
| 4 |
+
library_name: mlx
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
language: [ko, en]
|
| 7 |
+
tags: [moe, pruning, reap, k-reap, mlx, korean, expert-pruning]
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Qwen3-Coder-16B-A3B-KREAP-MLX (50% routed pruning)
|
| 11 |
+
|
| 12 |
+
Korean-preserving one-shot MoE expert pruning of [Qwen3-Coder-30B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct), produced with [**K-REAP**](https://github.com/Chedrian07/K-REAP). Routed experts pruned **128 → 64** per layer (50%); ~16B total params, 3.3B active (top-8 unchanged). No fine-tuning.
|
| 13 |
+
|
| 14 |
+
Unlike vanilla REAP (English/code calibration), K-REAP detects and **hard-protects the experts that carry Korean**, so pruning preserves Korean without sacrificing English/coding. See [K-Guard-REAP](https://github.com/Chedrian07/K-Guard-REAP) for the full study.
|
| 15 |
+
|
| 16 |
+
## Korean loss minimized vs. standard REAP
|
| 17 |
+
|
| 18 |
+
The standard REAP recipe collapses Korean at comparable compression: Cerebras **Qwen3-Coder-REAP-25B** (19.5%, no language protection) drops Korean MC macro **79.3 → 56.6 (−22.7pp)** with generation collapse **115/128**. By hard-protecting the Korean expert path, **this model keeps Korean MC macro at 67.3 (−12.0pp) with 52/128 collapse** — still well ahead of REAP's 56.6 / 115 even at this aggressive ratio. (K-REAP removes ~47% of REAP's Korean damage.)
|
| 19 |
+
|
| 20 |
+
> **⚠️ Compression-ceiling model.** At 50% the per-layer protected set (up to 83) no longer fits the budget (64), so 93 Korean-protected experts were force-dropped. Korean **and** English reasoning degrade here — this checkpoint documents the limit, not a recommended operating point. Use 12.5–25% for preserved Korean.
|
| 21 |
+
|
| 22 |
+
## Benchmarks (vs base Qwen3-Coder-30B; Δ = base delta, %p)
|
| 23 |
+
|
| 24 |
+
### 한국어 (Korean, self-harness)
|
| 25 |
+
|
| 26 |
+
| benchmark | base | this model |
|
| 27 |
+
|---|---:|---:|
|
| 28 |
+
| KMMLU | 55.2 | 41.2 (−14.0) |
|
| 29 |
+
| KoBEST BoolQ | 93.6 | 80.4 (−13.2) |
|
| 30 |
+
| KoBEST COPA | 92.7 | 71.5 (−21.2) |
|
| 31 |
+
| KoBEST SentiNeg | 95.0 | 90.4 (−4.6) |
|
| 32 |
+
| KoBEST HellaSwag | 60.0 | 52.8 (−7.2) |
|
| 33 |
+
| Gen. collapse (/128, ↓) | 0 | 52 |
|
| 34 |
+
|
| 35 |
+
### English reasoning/knowledge (llm-evalbox)
|
| 36 |
+
|
| 37 |
+
| benchmark | base | this model |
|
| 38 |
+
|---|---:|---:|
|
| 39 |
+
| ARC-Challenge | 91.2 | 71.0 (−20.2) |
|
| 40 |
+
| HellaSwag | 84.4 | 63.4 (−21.0) |
|
| 41 |
+
| WinoGrande | 73.4 | 57.6 (−15.8) |
|
| 42 |
+
| MMLU-Pro | 50.2 | 37.0 (−13.2) |
|
| 43 |
+
| TruthfulQA | 71.2 | 46.6 (−24.6) |
|
| 44 |
+
| MMLU-en | 76.6 | 54.6 (−22.0) |
|
| 45 |
+
|
| 46 |
+
### Math
|
| 47 |
+
|
| 48 |
+
| benchmark | base | this model |
|
| 49 |
+
|---|---:|---:|
|
| 50 |
+
| GSM8K | 93.2 | 80.2 (−13.0) |
|
| 51 |
+
| MathQA | 55.2 | 33.8 (−21.4) |
|
| 52 |
+
|
| 53 |
+
### Coding
|
| 54 |
+
|
| 55 |
+
| benchmark | base | this model |
|
| 56 |
+
|---|---:|---:|
|
| 57 |
+
| HumanEval+ | 87.8 | 79.3 (−8.5) |
|
| 58 |
+
| MBPP+ | 77.2 | 59.3 (−17.9) |
|
| 59 |
+
| LiveCodeBench | 52.4 | 27.9 (−24.5) |
|
| 60 |
+
|
| 61 |
+
### Safety/Bias
|
| 62 |
+
|
| 63 |
+
| benchmark | base | this model |
|
| 64 |
+
|---|---:|---:|
|
| 65 |
+
| BBQ | 92.2 | 66.8 (−25.4) |
|
| 66 |
+
| SafetyBench | 83.2 | 73.4 (−9.8) |
|
| 67 |
+
|
| 68 |
+
### Macro
|
| 69 |
+
|
| 70 |
+
| benchmark | base | this model |
|
| 71 |
+
|---|---:|---:|
|
| 72 |
+
| Korean MC macro | 79.3 | 67.3 (−12.0) |
|
| 73 |
+
| Academic 10-bench macro | 74.7 | 55.8 (−18.9) |
|
| 74 |
+
|
| 75 |
+
## Usage (MLX)
|
| 76 |
+
|
| 77 |
+
```python
|
| 78 |
+
from mlx_lm import load, generate
|
| 79 |
+
model, tok = load("KCh3dRi4n/Qwen3-coder-16B-A3B-KREAP-MLX")
|
| 80 |
+
print(generate(model, tok, prompt="한국어로 자기소개를 해줘.", max_tokens=256))
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
Standard HF safetensors (BF16) — also loadable with `transformers`. Coverage note: KoBEST & EvalPlus are full sets; KMMLU/evalbox/LiveCodeBench are deterministic subsets (seed 42). Effect sizes ≫ sampling CI. Details: K-Guard-REAP `docs/10_MASTER_RESULTS.md §7`.
|
| 84 |
+
|
| 85 |
+
## Method
|
| 86 |
+
|
| 87 |
+
REAP saliency (router gate × expert-output L2 norm, conditional mean) restricted to Korean segments + Korean↔English contrast + rare/rollout protection → hard-protected survivor set → streaming safetensors surgery (uniform experts/layer). Framework: https://github.com/Chedrian07/K-REAP
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_extra_keys(json_dict, handled_keys) %}
|
| 2 |
+
{%- if json_dict is mapping %}
|
| 3 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 4 |
+
{%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
|
| 5 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- endfor %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{% endmacro %}
|
| 12 |
+
|
| 13 |
+
{%- if messages[0]["role"] == "system" %}
|
| 14 |
+
{%- set system_message = messages[0]["content"] %}
|
| 15 |
+
{%- set loop_messages = messages[1:] %}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{%- set loop_messages = messages %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
|
| 20 |
+
{%- if not tools is defined %}
|
| 21 |
+
{%- set tools = [] %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
|
| 24 |
+
{%- if system_message is defined %}
|
| 25 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 28 |
+
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 32 |
+
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 33 |
+
{{- "<tools>" }}
|
| 34 |
+
{%- for tool in tools %}
|
| 35 |
+
{%- if tool.function is defined %}
|
| 36 |
+
{%- set tool = tool.function %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 39 |
+
{%- if tool.description is defined %}
|
| 40 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- '\n<parameters>' }}
|
| 43 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 44 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 45 |
+
{{- '\n<parameter>' }}
|
| 46 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 47 |
+
{%- if param_fields.type is defined %}
|
| 48 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- if param_fields.description is defined %}
|
| 51 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set handled_keys = ['name', 'type', 'description'] %}
|
| 54 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 55 |
+
{{- '\n</parameter>' }}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{% set handled_keys = ['type', 'properties'] %}
|
| 59 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 60 |
+
{{- '\n</parameters>' }}
|
| 61 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 62 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 63 |
+
{{- '\n</function>' }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- if system_message is defined %}
|
| 69 |
+
{{- '<|im_end|>\n' }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 72 |
+
{{- '<|im_end|>\n' }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- for message in loop_messages %}
|
| 76 |
+
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 77 |
+
{{- '<|im_start|>' + message.role }}
|
| 78 |
+
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
|
| 79 |
+
{{- '\n' + message.content | trim + '\n' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for tool_call in message.tool_calls %}
|
| 82 |
+
{%- if tool_call.function is defined %}
|
| 83 |
+
{%- set tool_call = tool_call.function %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 86 |
+
{%- if tool_call.arguments is defined %}
|
| 87 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 88 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 89 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 90 |
+
{{- args_value }}
|
| 91 |
+
{{- '\n</parameter>\n' }}
|
| 92 |
+
{%- endfor %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '</function>\n</tool_call>' }}
|
| 95 |
+
{%- endfor %}
|
| 96 |
+
{{- '<|im_end|>\n' }}
|
| 97 |
+
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
| 98 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 99 |
+
{%- elif message.role == "tool" %}
|
| 100 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 101 |
+
{{- '<|im_start|>user\n' }}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{{- '<tool_response>\n' }}
|
| 104 |
+
{{- message.content }}
|
| 105 |
+
{{- '\n</tool_response>\n' }}
|
| 106 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 107 |
+
{{- '<|im_end|>\n' }}
|
| 108 |
+
{%- elif loop.last %}
|
| 109 |
+
{{- '<|im_end|>\n' }}
|
| 110 |
+
{%- endif %}
|
| 111 |
+
{%- else %}
|
| 112 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 113 |
+
{%- endif %}
|
| 114 |
+
{%- endfor %}
|
| 115 |
+
{%- if add_generation_prompt %}
|
| 116 |
+
{{- '<|im_start|>assistant\n' }}
|
| 117 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"decoder_sparse_step": 1,
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 6144,
|
| 15 |
+
"max_position_embeddings": 262144,
|
| 16 |
+
"max_window_layers": 48,
|
| 17 |
+
"mlp_only_layers": [],
|
| 18 |
+
"model_type": "qwen3_moe",
|
| 19 |
+
"moe_intermediate_size": 768,
|
| 20 |
+
"norm_topk_prob": true,
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_experts": 64,
|
| 23 |
+
"num_experts_per_tok": 8,
|
| 24 |
+
"num_hidden_layers": 48,
|
| 25 |
+
"num_key_value_heads": 4,
|
| 26 |
+
"output_router_logits": false,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_scaling": null,
|
| 29 |
+
"rope_theta": 10000000,
|
| 30 |
+
"router_aux_loss_coef": 0.001,
|
| 31 |
+
"sliding_window": null,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"torch_dtype": "bfloat16",
|
| 34 |
+
"transformers_version": "4.52.3",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 151936
|
| 38 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"pad_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_p": 0.8,
|
| 11 |
+
"top_k": 20
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa7c8827e0a77da090a23df845ae58eb20ed0189811e8c544327153c9bc03ef2
|
| 3 |
+
size 2365671808
|
model-00002-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68bd17528749ac12c578b7fefc5932fbee9e9fa7bc6f2c447e0028896da882be
|
| 3 |
+
size 2070780592
|
model-00003-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3530ded48c93cc05a2f524a24f72c05921bff377a388447bdc819ca8450af42
|
| 3 |
+
size 2039592456
|
model-00004-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59fc84f783d8cef9ea97a3e2351d728d5f3de22dc0657f267ab6e81685e8bd7f
|
| 3 |
+
size 2089656160
|
model-00005-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e647be34b3e7b8b8ce89a5b00a0abd671b40e63ffddf2bf85471eadea8ce7fd9
|
| 3 |
+
size 2064489528
|
model-00006-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0971ecbe2504fdd18cbd192e888537ff4f4eb1c4d5cd4660b8c88679aa71e1e
|
| 3 |
+
size 2055051976
|
model-00007-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c50e5157d74e40503bff6c703dbc132bf0fa9a65710891a26449426a2fb9d699
|
| 3 |
+
size 2036176864
|
model-00008-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e51647760b06b6ce5ac498040df29bcfdf9edc7d327352c55c598abd9c78ce7e
|
| 3 |
+
size 2099364264
|
model-00009-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42f209f5b690ba446f7da0342ff0193d504b3e4ea4e9200ebee6726e5811e76e
|
| 3 |
+
size 2042468560
|
model-00010-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:863b6dee18e9b8b70d7eaf9978c58eac1eb52c8d8cf9d08c4c2a7cd3ea55dbd4
|
| 3 |
+
size 2086510496
|
model-00011-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc4de0e715b9b2c81cea3d02d05d136e241a09e54185574819b294a3e40d5a59
|
| 3 |
+
size 1982697376
|
model-00012-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b559534a320f1b94ea470755fd2e0ee21a22e57c6835b9f66bdb9c4ff8fac58
|
| 3 |
+
size 2086781176
|
model-00013-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a7a9ac618a0f5286f2416348179b433db7dd53b76fa31bcd5bace2847ebb12d
|
| 3 |
+
size 2083364336
|
model-00014-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b4df426722b474a0e2322b69f9abb5a3d815f21546d3ec9ab5440e0d4f16436
|
| 3 |
+
size 2051906120
|
model-00015-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c14223d4e52fa052415598e50d01e8203824ecaedfc6b7280a173c18acea441e
|
| 3 |
+
size 2077072944
|
model-00016-of-00016.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c1e2a24c6005217296a0109865c217c7e29de35a5dbc4b10fd67c8e83246ac7
|
| 3 |
+
size 830230960
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tensor_hash_validation.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"src": "/Volumes/Back_UP_LLM/hf_cache/models--Qwen--Qwen3-Coder-30B-A3B-Instruct/snapshots/b2cff646eb4bb1d68355c01b18ae02e7cf42d120",
|
| 3 |
+
"out": "/Volumes/Back_UP_LLM/kguard-artifacts/checkpoints/kguard-64",
|
| 4 |
+
"num_experts_kept": 64,
|
| 5 |
+
"untouched_tensors_checked": 387,
|
| 6 |
+
"hash_mismatches": [],
|
| 7 |
+
"total_bytes": 32060633088,
|
| 8 |
+
"expert_count_ok": true,
|
| 9 |
+
"hash_ok": true
|
| 10 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"151665": {
|
| 181 |
+
"content": "<tool_response>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"151666": {
|
| 189 |
+
"content": "</tool_response>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"151667": {
|
| 197 |
+
"content": "<think>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
+
},
|
| 204 |
+
"151668": {
|
| 205 |
+
"content": "</think>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": false
|
| 211 |
+
}
|
| 212 |
+
},
|
| 213 |
+
"additional_special_tokens": [
|
| 214 |
+
"<|im_start|>",
|
| 215 |
+
"<|im_end|>",
|
| 216 |
+
"<|object_ref_start|>",
|
| 217 |
+
"<|object_ref_end|>",
|
| 218 |
+
"<|box_start|>",
|
| 219 |
+
"<|box_end|>",
|
| 220 |
+
"<|quad_start|>",
|
| 221 |
+
"<|quad_end|>",
|
| 222 |
+
"<|vision_start|>",
|
| 223 |
+
"<|vision_end|>",
|
| 224 |
+
"<|vision_pad|>",
|
| 225 |
+
"<|image_pad|>",
|
| 226 |
+
"<|video_pad|>"
|
| 227 |
+
],
|
| 228 |
+
"bos_token": null,
|
| 229 |
+
"chat_template": "{% macro render_extra_keys(json_dict, handled_keys) %}\n {%- if json_dict is mapping %}\n {%- for json_key in json_dict if json_key not in handled_keys %}\n {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}\n {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n {%- else %}\n {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{% endmacro %}\n\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{%- if not tools is defined %}\n {%- set tools = [] %}\n{%- endif %}\n\n{%- if system_message is defined %}\n {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n {%- if tools is iterable and tools | length > 0 %}\n {{- \"<|im_start|>system\\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks.\" }}\n {%- endif %}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n {{- \"\\n\\n# Tools\\n\\nYou have access to the following functions:\\n\\n\" }}\n {{- \"<tools>\" }}\n {%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n {%- if tool.description is defined %}\n {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n {%- endif %}\n {{- '\\n<parameters>' }}\n {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- '\\n<parameter>' }}\n {{- '\\n<name>' ~ param_name ~ '</name>' }}\n {%- if param_fields.type is defined %}\n {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n {%- endif %}\n {%- if param_fields.description is defined %}\n {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n {%- endif %}\n {%- set handled_keys = ['name', 'type', 'description'] %}\n {{- render_extra_keys(param_fields, handled_keys) }}\n {{- '\\n</parameter>' }}\n {%- endfor %}\n {%- endif %}\n {% set handled_keys = ['type', 'properties'] %}\n {{- render_extra_keys(tool.parameters, handled_keys) }}\n {{- '\\n</parameters>' }}\n {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}\n {{- render_extra_keys(tool, handled_keys) }}\n {{- '\\n</function>' }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n{%- endif %}\n{%- if system_message is defined %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if tools is iterable and tools | length > 0 %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in loop_messages %}\n {%- if message.role == \"assistant\" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}\n {{- '\\n' + message.content | trim + '\\n' }}\n {%- endif %}\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<tool_call>\\n<function=' + tool_call.name + '>\\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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"user\" or message.role == \"system\" or message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user\\n' }}\n {%- endif %}\n {{- '<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"model_max_length": 1048576,
|
| 234 |
+
"pad_token": "<|endoftext|>",
|
| 235 |
+
"split_special_tokens": false,
|
| 236 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 237 |
+
"unk_token": null,
|
| 238 |
+
"add_bos_token": false
|
| 239 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|