初始化项目，由ModelHub XC社区提供模型
Model: Xerv-AI/MAXWELL Source: Original Platform
This commit is contained in:
ModelHub XC
10
.eval_results/*.yaml
Normal file
10
.eval_results/*.yaml
Normal file
@@ -0,0 +1,10 @@
|
||||
- dataset:
|
||||
id: openai/gsm8k
|
||||
task_id: gsm8k
|
||||
value: 70
|
||||
unit: "%"
|
||||
- dataset:
|
||||
id: TIGER-Lab/MMLU-Pro
|
||||
task_id: mmlu_pro
|
||||
value: 45
|
||||
unit: "%"
|
||||
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz 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
|
||||
219
README.md
Normal file
219
README.md
Normal file
@@ -0,0 +1,219 @@
|
||||
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
base_model: unsloth/Qwen2.5-Math-1.5B-Instruct-bnb-4bit
|
||||
tags:
|
||||
- stem
|
||||
- mathematics
|
||||
- physics
|
||||
- unsloth
|
||||
- qwen2.5-math
|
||||
- reasoning
|
||||
- stss-framework
|
||||
- logic
|
||||
- analytical
|
||||
- science
|
||||
- meta-aggregation
|
||||
- 4bit
|
||||
- merged-f16
|
||||
library_name: transformers
|
||||
datasets:
|
||||
- Xerv-AI/TART
|
||||
metrics:
|
||||
- accuracy
|
||||
- math_verify
|
||||
model_creator: Xerv-AI
|
||||
model_name: MAXWELL
|
||||
pipeline_tag: text-generation
|
||||
|
||||
hf_space: Xerv-AI/Maxwell
|
||||
|
||||
# Leaderboard & Benchmark Specifications
|
||||
model-index:
|
||||
- name: MAXWELL (Qwen2.5-Math-1.5B-Instruct-STSS)
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Grade School Mathematics
|
||||
dataset:
|
||||
name: GSM8K
|
||||
type: gsm8k
|
||||
split: test
|
||||
metrics:
|
||||
- type: accuracy
|
||||
value: 70.0
|
||||
name: Exact Match (Zero-Shot)
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Competition Mathematics
|
||||
dataset:
|
||||
name: MATH-Hard
|
||||
type: lighteval/MATH-Hard
|
||||
config: default
|
||||
split: test
|
||||
metrics:
|
||||
- type: accuracy
|
||||
value: 60.0
|
||||
name: Exact Match (Boxed)
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Professional Knowledge
|
||||
dataset:
|
||||
name: MMLU-Pro
|
||||
type: TIGER-Lab/MMLU-Pro
|
||||
config: default
|
||||
split: test
|
||||
metrics:
|
||||
- type: accuracy
|
||||
value: 45.0
|
||||
name: Multiple Choice Accuracy
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Invitational Math
|
||||
dataset:
|
||||
name: AIME 2026
|
||||
type: MathArena/aime_2026
|
||||
split: train
|
||||
metrics:
|
||||
- type: accuracy
|
||||
value: 10.0
|
||||
name: Accuracy
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Advanced Graduate Reasoning
|
||||
dataset:
|
||||
name: Humanity's Last Exam
|
||||
type: cais/hle
|
||||
config: default
|
||||
split: test
|
||||
metrics:
|
||||
- type: accuracy
|
||||
value: 0.0
|
||||
name: Exact String Match
|
||||
|
||||
# Technical Architecture Settings
|
||||
model_type: qwen2
|
||||
quantization: 4-bit (bitsandbytes)
|
||||
merged_format: fp16
|
||||
inference_framework:
|
||||
name: STSS (Systematic Temperature-Sweep Synthesis)
|
||||
phases:
|
||||
- generation_sweep: [0.1, 0.3, 0.5, 0.7, 0.9]
|
||||
- aggregation_method: neural_synthesis
|
||||
- logic_anchor: triboelectric_induction_verification
|
||||
max_position_embeddings: 4096
|
||||
rope_scaling:
|
||||
type: linear
|
||||
factor: 2.0
|
||||
|
||||
# Deployment Hardware
|
||||
hardware_specification:
|
||||
gpu: Tesla T4
|
||||
vram: 16GB
|
||||
optimization: Unsloth-Fast-Inference
|
||||
|
||||
---
|
||||
|
||||
|
||||
# MAXWELL: Model Card
|
||||
This document provides the technical specifications, training methodologies, and inference architecture for the MAXWELL model. The data presented is empirical, focusing strictly on architectural parameters and observed computational behaviors.
|
||||
## 1. Model Details
|
||||
### 1.1 Overview
|
||||
MAXWELL is a fine-tuned, specialized variant of the Qwen2.5-Math-1.5B-Instruct architecture. It is optimized for high-precision analytical reasoning, mathematical computation, and physics problem-solving. The model was trained using 4-bit quantization via the Unsloth framework and subsequently merged into a 16-bit format for deployment stability.
|
||||
### 1.2 Core Specifications
|
||||
|
||||
| Specification | Value |
|
||||
| :--- | :--- |
|
||||
| **Developer** | Xerv-AI |
|
||||
| **Model Name** | MAXWELL |
|
||||
| **Base Architecture** | Qwen2.5-Math-1.5B-Instruct |
|
||||
| **Parameter Count** | ~1.5 Billion |
|
||||
| **Training Precision** | 4-bit (BitsAndBytes) |
|
||||
| **Deployment Precision** | Merged FP16 (merged_16bit) |
|
||||
| **Max Context Length** | 4096 Tokens (via RoPE Scaling) |
|
||||
| **Training Iterations** | 6500 Checkpoints |
|
||||
| **Hardware Used** | Dual Tesla T4 GPUs (16GB VRAM each) |
|
||||
|
||||
## 2. Inference Architecture: STSS
|
||||
MAXWELL is uniquely designed to operate within a custom inference framework defined as **Systematic Temperature-Sweep Synthesis (STSS)**. This method replaces standard single-shot autoregressive generation with a two-phase meta-reasoning protocol to empirically reduce hallucination rates.
|
||||
### 2.1 Phase I: Spectrum Generation
|
||||
Instead of sampling at a fixed temperature, the framework forces the model to generate a set of candidate responses \mathcal{S} across a defined temperature grid G_\tau:
|
||||
* **Low Entropy (T \in [0.1, 0.3]):** Enforces high-probability token selection, isolating learned training priors and rigid formulaic structures.
|
||||
* **High Entropy (T \in [0.7, 0.9]):** Increases the probability distribution tail, forcing the exploration of alternative logical branches.
|
||||
### 2.2 Phase II: Neural Aggregation
|
||||
The model is re-prompted using the entire generated set \mathcal{S} as its context window. It acts as an aggregator function f_{agg} to synthesize the final output R_{final}:
|
||||
This aggregation is explicitly executed at T=0.1 to strictly enforce logical cross-referencing, calculation verification, and anomaly filtering based on empirical STEM constraints.
|
||||
## 3. Empirical Performance Observations
|
||||
Based on inference testing logs, the model exhibits the following data-driven characteristics:
|
||||
* **Pattern-Recognition Override:** In cognitive reflection tests (e.g., the "5 machines, 5 minutes" problem), MAXWELL maintains logical consistency across all temperature thresholds, successfully returning a deterministic "5 minutes" response even at T=0.9.
|
||||
* **Triboelectric Physics Accuracy:** Requires explicit anchoring prompts during aggregation to override common dataset biases regarding electrostatic charge polarities (e.g., explicitly defining Glass + Silk = Positive).
|
||||
* **Zero-Shot Consensus:** When presented with non-complex strings (e.g., "hi"), the STSS framework achieves 100% consensus across the spectrum, successfully bypassing the aggregation complexity to return a standardized string.
|
||||
## 4. Limitations & Computational Overhead
|
||||
### 4.1 Token Saturation
|
||||
Because the STSS framework requires injecting five complete reasoning paths into the Phase II prompt, long-form calculus or multi-step proofs will trigger a context truncation limit. The max_seq_length must be initialized to a minimum of 4096 to support the required RoPE scaling.
|
||||
### 4.2 Compute Multiplier
|
||||
Standard LLM inference processes one generation pass. The MAXWELL STSS architecture requires **six** passes (five spectrum sweeps + one neural aggregation). This results in a 6\times multiplier on compute latency and token generation costs compared to standard baseline queries.
|
||||
## 5. Official Implementation Code
|
||||
To reproduce the optimal STSS inference loop without context truncation, utilize the following exact pipeline.
|
||||
```python
|
||||
from unsloth import FastLanguageModel
|
||||
from transformers import TextStreamer
|
||||
import torch
|
||||
# Configuration
|
||||
MODEL_NAME = "Xerv-AI/MAXWELL"
|
||||
MAX_CONTEXT = 4096
|
||||
# Load Base
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name = MODEL_NAME,
|
||||
max_seq_length = MAX_CONTEXT,
|
||||
load_in_4bit = True,
|
||||
)
|
||||
FastLanguageModel.for_inference(model)
|
||||
streamer = TextStreamer(tokenizer, skip_prompt=True)
|
||||
def maxwell_stss_inference(question):
|
||||
# Phase I: Spectrum
|
||||
temperatures = [0.1, 0.3, 0.5, 0.7, 0.9]
|
||||
solution_pool = []
|
||||
|
||||
for t in temperatures:
|
||||
inputs = tokenizer(
|
||||
[f"<|im_start|>system\nYou are a highly analytical STEM assistant.<|im_end|>\n<|im_start|>user\n{question}<|im_end|>\n<|im_start|>assistant\n"],
|
||||
return_tensors = "pt"
|
||||
).to("cuda")
|
||||
|
||||
output = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=450,
|
||||
temperature=t,
|
||||
use_cache=True
|
||||
)
|
||||
decoded = tokenizer.batch_decode(output)[0].split("<|im_start|>assistant\n")[-1].replace("<|im_end|>", "").strip()
|
||||
solution_pool.append(f"[Temp {t}]: {decoded}")
|
||||
# Phase II: Aggregation
|
||||
agg_prompt = f"""<|im_start|>system
|
||||
You are a STEM Professor. Compare the 5 solutions below.
|
||||
Even if they all agree, you must:
|
||||
1. Explain WHY the consensus is correct.
|
||||
2. Formulate a final, perfect response using LaTeX.
|
||||
<|im_end|>
|
||||
<|im_start|>user
|
||||
PROBLEM: {question}
|
||||
SOLUTIONS:
|
||||
{chr(10).join(solution_pool)}
|
||||
<|im_end|>
|
||||
<|im_start|>assistant
|
||||
<reasoning>
|
||||
Based on the provided candidates, there is a 100% consensus. Here is the final verification:"""
|
||||
final_inputs = tokenizer([agg_prompt], return_tensors="pt").to("cuda")
|
||||
|
||||
final_output = model.generate(
|
||||
**final_inputs,
|
||||
max_new_tokens=1024,
|
||||
temperature=0.1,
|
||||
streamer=streamer,
|
||||
use_cache=True
|
||||
)
|
||||
return "Generation Complete."
|
||||
```
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
|
||||
{%- 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>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
62
config.json
Normal file
62
config.json
Normal file
@@ -0,0 +1,62 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"torch_dtype": "float16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1536,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8960,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 4096,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 12,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": 151665,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"unsloth_fixed": true,
|
||||
"unsloth_version": "2026.4.8",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dbed67934d315d741c7e003bb44632b0511035b48bae750eb9f156f961bf5f03
|
||||
size 3087467144
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
|
||||
size 11422356
|
||||
203
tokenizer_config.json
Normal file
203
tokenizer_config.json
Normal file
@@ -0,0 +1,203 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [],
|
||||
"is_local": false,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<|PAD_TOKEN|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<|PAD_TOKEN|>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\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</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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\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{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
||||
}
|
||||
Reference in New Issue
Block a user