初始化项目，由ModelHub XC社区提供模型
Model: kz919/QwQ-0.5B-Distilled-SFT Source: Original Platform
This commit is contained in:
ModelHub XC
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
|
||||
205
README.md
Normal file
205
README.md
Normal file
@@ -0,0 +1,205 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- amphora/QwQ-LongCoT-130K-2
|
||||
- PowerInfer/QWQ-LONGCOT-500K
|
||||
- PowerInfer/LONGCOT-Refine-500K
|
||||
language:
|
||||
- en
|
||||
metrics:
|
||||
- perplexity
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-0.5B-Instruct
|
||||
library_name: transformers
|
||||
---
|
||||
## Model Details:
|
||||
|
||||
- **Base Model:** Qwen/Qwen2-0.5B-Instruct
|
||||
- **Teacher Model:** Qwen/QwQ-32B-Preview
|
||||
- **Distillation Framework:** Instruction Tuning
|
||||
- **Task Type:** Conversational AI / Causal Language Modeling
|
||||
- **Parameters:** 0.5B
|
||||
- **Special Features:**
|
||||
- Integrated gradient checkpointing for efficient training
|
||||
- Step-by-step reasoning capabilities for better problem-solving
|
||||
|
||||
---
|
||||
|
||||
## Training:
|
||||
|
||||
QwQ-0.5B-Distilled was trained using the **QwQ-LongCoT-130K dataset**, a carefully curated collection of long-context examples designed for reasoning and conversational AI tasks. The GKD framework ensures that the student model mimics the teacher model’s outputs, aligning its predictions with high-quality responses.
|
||||
### Training Progress:
|
||||
[▓▓▓▓▓▓▓▓▓▓] 100%
|
||||
|
||||
### Training Script:
|
||||
|
||||
```python
|
||||
import os
|
||||
import argparse
|
||||
import torch
|
||||
from datasets import Dataset
|
||||
from trl import SFTConfig, SFTTrainer, DataCollatorForCompletionOnlyLM
|
||||
from transformers import (
|
||||
AutoModelForCausalLM,
|
||||
AutoTokenizer,
|
||||
)
|
||||
from datasets import load_dataset
|
||||
from peft import LoraConfig
|
||||
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--max_length", type=int, default = 4096)
|
||||
parser.add_argument("--output_dir", type=str, default="gkd-model")
|
||||
parser.add_argument("--per_device_train_batch_size", type=int, default=1)
|
||||
parser.add_argument("--gradient_accumulation_steps", type=int, default=16)
|
||||
parser.add_argument("--gradient_checkpointing", action="store_true", default=False)
|
||||
parser.add_argument("--resume_from_checkpoint", action="store_true", default=False)
|
||||
parser.add_argument("--lora", action="store_true")
|
||||
args = parser.parse_args()
|
||||
|
||||
qwq_dataset = load_dataset("amphora/QwQ-LongCoT-130K-2", split = "train")
|
||||
messages = []
|
||||
for each in qwq_dataset:
|
||||
msg = [
|
||||
{"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
|
||||
{"role": "user", "content": each["problem"]},
|
||||
{"role": "assistant", "content": each["qwq"]},
|
||||
]
|
||||
messages.append(msg)
|
||||
|
||||
TRAIN_SPLIT_RATIO = 0.9
|
||||
train_size = int(TRAIN_SPLIT_RATIO * len(messages))
|
||||
eval_size = len(messages) - train_size
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
|
||||
|
||||
# The model to optimise
|
||||
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
|
||||
|
||||
### Real Dataset
|
||||
train_dataset = Dataset.from_dict({"messages":messages[:train_size]})
|
||||
eval_dataset = Dataset.from_dict({"messages":messages[train_size:]})
|
||||
training_args = SFTConfig(
|
||||
output_dir=args.output_dir,
|
||||
max_seq_length=args.max_length,
|
||||
per_device_train_batch_size=args.per_device_train_batch_size,
|
||||
gradient_accumulation_steps=args.gradient_accumulation_steps,
|
||||
gradient_checkpointing = args.gradient_checkpointing,
|
||||
save_steps = 100,
|
||||
save_total_limit = 5
|
||||
)
|
||||
|
||||
lora_config = LoraConfig(
|
||||
r=16,
|
||||
lora_alpha=32,
|
||||
lora_dropout=0.05,
|
||||
bias="none",
|
||||
task_type="CAUSAL_LM",
|
||||
)
|
||||
|
||||
response_template = "<|im_start|>assistant\n"
|
||||
|
||||
collator = DataCollatorForCompletionOnlyLM(response_template, tokenizer=tokenizer)
|
||||
|
||||
trainer = SFTTrainer(
|
||||
model=model,
|
||||
args=training_args,
|
||||
processing_class=tokenizer,
|
||||
train_dataset=train_dataset,
|
||||
eval_dataset=eval_dataset,
|
||||
peft_config=lora_config if args.lora else None,
|
||||
data_collator=collator,
|
||||
)
|
||||
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)
|
||||
```
|
||||
|
||||
### Dataset:
|
||||
- **Source:** `amphora/QwQ-LongCoT-130K`
|
||||
- **Split:** 90% Training, 10% Evaluation
|
||||
|
||||
---
|
||||
|
||||
## Example Usage:
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
# Model name
|
||||
model_name = "kz919/QwQ-0.5B-Distilled-SFT"
|
||||
# Load the model
|
||||
print(f"Starting to load the model {model_name} into memory")
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
torch_dtype=torch.bfloat16,
|
||||
device_map={"": 0}
|
||||
)
|
||||
# Load the tokenizer
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
# Define the prompt
|
||||
prompt = "How many r in strawberry."
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
# Tokenize the input
|
||||
text = tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True
|
||||
)
|
||||
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||
# Generate a response
|
||||
generated_ids = model.generate(
|
||||
**model_inputs,
|
||||
max_new_tokens=4096
|
||||
)
|
||||
generated_ids = [
|
||||
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||||
]
|
||||
# Decode the response
|
||||
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
||||
print(response)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Applications:
|
||||
|
||||
1. **Conversational Assistants:**
|
||||
Suitable for AI chatbots that require reasoning and long-context understanding.
|
||||
|
||||
2. **Educational Tools:**
|
||||
Provides step-by-step explanations, making it ideal for learning environments.
|
||||
|
||||
3. **Creative Writing:**
|
||||
Assists in generating coherent, contextually aware long-form content.
|
||||
|
||||
4. **Technical Support:**
|
||||
Handles complex customer queries with precision and clarity.
|
||||
|
||||
---
|
||||
|
||||
## Limitations:
|
||||
|
||||
- While distilled for efficiency, performance on highly complex reasoning tasks may slightly trail the teacher model.
|
||||
- This model could still be under trained, merely a proof of concept. Don't yell at me if it's outputing nonesense.
|
||||
---
|
||||
|
||||
## Citation:
|
||||
|
||||
If you use this model in your research or applications, please cite it as:
|
||||
|
||||
```bibtex
|
||||
@model{qwq_0.5B_distilled,
|
||||
author = {Kaizhao Liang},
|
||||
title = {Mini-QwQ: A Reasoning Model for Edge Devices},
|
||||
year = {2024},
|
||||
publisher = {Hugging Face},
|
||||
version = {1.0}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
This model is an example of how efficient fine-tuning and distillation methods can deliver robust conversational AI capabilities in a smaller, more manageable footprint.
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/scratch/09979/kaizhaol/sft_model_8dp_small_batch_v6/checkpoint-25617/",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 896,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4864,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 21,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 24,
|
||||
"num_key_value_heads": 2,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.47.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.1,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.47.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ea4ec15efbcce35975c0fba5f3847488a2f062bdbbac8b5b94cbd6ecaf0b492d
|
||||
size 988097824
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user