baichuan-inc/Baichuan-M2-32B-GPTQ-Int4
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: baichuan-inc/Baichuan-M2-32B-GPTQ-Int4
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-08 16:14:15 +08:00
commit 6aad305542
21 changed files with 3572 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
.gitattributes vendored Normal file
View File

@@ -0,0 +1,51 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

202
LICENSE Normal file
View File

@@ -0,0 +1,202 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright 2024 Alibaba Cloud
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

138
README.md Normal file
View File

@@ -0,0 +1,138 @@
---
license: apache-2.0
tags:
- chat
library_name: transformers
language:
- en
- zh
base_model:
- Qwen/Qwen2.5-32B
---
# Baichuan-M2-32B-GPTQ-Int4
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Hugging Face](https://img.shields.io/badge/🤗%20Hugging%20Face-Model-yellow)](https://huggingface.co/baichuan-inc/Baichuan-M2-32B)
[![M2 GPTQ-4bit](https://img.shields.io/badge/🤗%20M2%20GPTQ--4bit-Model-orange)](https://huggingface.co/baichuan-inc/Baichuan-M2-32B-GPTQ-Int4)
[![Huawei Ascend 8bit](https://img.shields.io/badge/✨%20Huawei%20Ascend%208bit-Model-green)](https://modelers.cn/models/Baichuan/Baichuan-M2-32B-W8A8)
## 🌟 Model Overview
Baichuan-M2-32B is Baichuan AI's medical-enhanced reasoning model, the second medical model released by Baichuan. Designed for real-world medical reasoning tasks, this model builds upon Qwen2.5-32B with an innovative Large Verifier System. Through domain-specific fine-tuning on real-world medical questions, it achieves breakthrough medical performance while maintaining strong general capabilities.
**Model Features:**
Baichuan-M2 incorporates three core technical innovations: First, through the **Large Verifier System**, it combines medical scenario characteristics to design a comprehensive medical verification framework, including patient simulators and multi-dimensional verification mechanisms; second, through **medical domain adaptation enhancement** via Mid-Training, it achieves lightweight and efficient medical domain adaptation while preserving general capabilities; finally, it employs a **multi-stage reinforcement learning** strategy, decomposing complex RL tasks into hierarchical training stages to progressively enhance the model's medical knowledge, reasoning, and patient interaction capabilities.
**Core Highlights:**
- 🏆 **World's Leading Open-Source Medical Model**: Outperforms all open-source models and many proprietary models on HealthBench, achieving medical capabilities closest to GPT-5
- 🧠 **Doctor-Thinking Alignment**: Trained on real clinical cases and patient simulators, with clinical diagnostic thinking and robust patient interaction capabilities
- ⚡ **Efficient Deployment**: Supports 4-bit quantization for single-RTX4090 deployment, with 58.5% higher token throughput in MTP version for single-user scenarios
## 📊 Performance Metrics
### HealthBench Scores
| Model Name | HealthBench | HealthBench-Hard | HealthBench-Consensus |
|------------|-------------|------------------|-----------------------|
| Baichuan-M2 | 60.1 | 34.7 | 91.5 |
| gpt-oss-120b | 57.6 | 30 | 90 |
| Qwen3-235B-A22B-Thinking-2507 | 55.2 | 25.9 | 90.6 |
| Deepseek-R1-0528 | 53.6 | 22.6 | 91.5 |
| GLM-4.5 | 47.8 | 18.7 | 85.3 |
| Kimi-K2 | 43 | 10.7 | 90.9 |
| gpt-oss-20b | 42.5 | 10.8 | 82.6 |
### General Performance
| Benchmark | Baichuan-M2-32B | Qwen3-32B (Thinking) |
|-----------|-----------------|-----------|
| AIME24 | 83.4 | 81.4 |
| AIME25 | 72.9 | 72.9 |
| Arena-Hard-v2.0 | 45.8 | 44.5 |
| CFBench | 77.6 | 75.7 |
| WritingBench | 8.56 | 7.90 |
*Note: AIME uses max_tokens=64k, others use 32k; temperature=0.6 for all tests.*
## 🔧 Technical Features
📗 **Technical Blog**: [Blog - Baichuan-M2](https://www.baichuan-ai.com/blog/baichuan-M2)
📑 **Technical Report**: [Arxiv - Baichuan-M2](https://arxiv.org/abs/2509.02208)
### Large Verifier System
- **Patient Simulator**: Virtual patient system based on real clinical cases
- **Multi-Dimensional Verification**: 8 dimensions including medical accuracy, response completeness, and follow-up awareness
- **Dynamic Scoring**: Real-time generation of adaptive evaluation criteria for complex clinical scenarios
### Medical Domain Adaptation
- **Mid-Training**: Medical knowledge injection while preserving general capabilities
- **Reinforcement Learning**: Multi-stage RL strategy optimization
- **General-Specialized Balance**: Carefully balanced medical, general, and mathematical composite training data
## ⚙️ Quick Start
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.9.0` or to create an OpenAI-compatible API endpoint:
- SGLang:
```shell
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3
```
To turn on kv cache FP8 quantization:
```shell
python -m sglang.launch_server --model-path baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv-cache-dtype fp8_e4m3 --attention-backend flashinfer
```
- vLLM:
```shell
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3
```
To turn on kv cache FP8 quantization:
```shell
vllm serve baichuan-inc/Baichuan-M2-32B-GPTQ-Int4 --reasoning-parser qwen3 --kv_cache_dtype fp8_e4m3
```
## MTP inference with SGLang
1. Replace the qwen2.py file in the sglang installation directory with draft/qwen2.py.
2. Launch sglang:
```
python3 -m sglang.launch_server \
--model Baichuan-M2-32B-GPTQ-Int4 \
--speculative-algorithm EAGLE3 \
--speculative-draft-model-path Baichuan-M2-32B-GPTQ-Int4/draft \
--speculative-num-steps 6 \
--speculative-eagle-topk 10 \
--speculative-num-draft-tokens 32 \
--mem-fraction 0.9 \
--cuda-graph-max-bs 2 \
--reasoning-parser qwen3 \
--dtype bfloat16
```
## ⚠️ Usage Notices
1. **Medical Disclaimer**: For research and reference only; cannot replace professional medical diagnosis or treatment
2. **Intended Use Cases**: Medical education, health consultation, clinical decision support
3. **Safe Use**: Recommended under guidance of medical professionals
## 📄 License
Licensed under the [Apache License 2.0](LICENSE). Research and commercial use permitted.
## 🤝 Acknowledgements
- Base Model: Qwen2.5-32B
- Training Framework: verl
- Inference Engines: vLLM, SGLang
- Quantization: AutoRound, GPTQ
Thank you to the open-source community. We commit to continuous contribution and advancement of healthcare AI.
## 📞 Contact Us
- Resources: [Baichuan AI Website](https://www.baichuan-ai.com)
- Technical Support: [GitHub](https://github.com/baichuan-inc)
---
<div align="center">
**Empowering Healthcare with AI, Making Health Accessible to All**
</div>

28
added_tokens.json Normal file
View File

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

40
config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 131072,
"max_window_layers": 64,
"model_type": "qwen2",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"quantization_config": {
"autoround_version": "0.5.1",
"bits": 4,
"damp_percent": 0.01,
"data_type": "int",
"desc_act": false,
"group_size": 128,
"nsamples": 512,
"quant_method": "gptq",
"sym": true,
"true_sequential": false
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.52.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

29
draft/config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"architectures": [
"LlamaForCausalLMEagle3"
],
"attention_dropout": 0.0,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 32768,
"max_window_layers": 64,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 1,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064,
"draft_vocab_size": 32000
}

3
draft/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f80f49be625de0c703ae279805a764b07377bae6d2a31468e75e12fbf2c17298
size 1534011812

641
draft/qwen2.py Normal file
View File

@@ -0,0 +1,641 @@
# Copyright 2023-2024 SGLang Team
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
# Adapted from llama2.py
# Modify details for the adaptation of Qwen2 model.
"""Inference-only Qwen2 model compatible with HuggingFace weights."""
import logging
from typing import Any, Dict, Iterable, Optional, Tuple, Union, List
import torch
from torch import nn
from sglang.srt.distributed import (
get_pp_group,
get_tensor_model_parallel_rank,
get_tensor_model_parallel_world_size,
)
from sglang.srt.layers.activation import SiluAndMul
from sglang.srt.layers.layernorm import RMSNorm
from sglang.srt.layers.linear import (
MergedColumnParallelLinear,
QKVParallelLinear,
RowParallelLinear,
)
from sglang.srt.layers.logits_processor import LogitsProcessor
from sglang.srt.layers.pooler import Pooler, PoolingType
from sglang.srt.layers.quantization.base_config import QuantizationConfig
from sglang.srt.layers.radix_attention import RadixAttention
from sglang.srt.layers.rotary_embedding import get_rope
from sglang.srt.layers.utils import PPMissingLayer, get_layer_id
from sglang.srt.layers.vocab_parallel_embedding import (
ParallelLMHead,
VocabParallelEmbedding,
)
from sglang.srt.managers.schedule_batch import global_server_args_dict
from sglang.srt.model_executor.forward_batch_info import ForwardBatch, PPProxyTensors
from sglang.srt.model_loader.weight_utils import (
default_weight_loader,
kv_cache_scales_loader,
)
from sglang.srt.utils import add_prefix, make_layers
Qwen2Config = None
logger = logging.getLogger(__name__)
class Qwen2MLP(nn.Module):
def __init__(
self,
hidden_size: int,
intermediate_size: int,
hidden_act: str,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
) -> None:
super().__init__()
self.gate_up_proj = MergedColumnParallelLinear(
hidden_size,
[intermediate_size] * 2,
bias=False,
quant_config=quant_config,
prefix=add_prefix("gate_up_proj", prefix),
)
self.down_proj = RowParallelLinear(
intermediate_size,
hidden_size,
bias=False,
quant_config=quant_config,
prefix=add_prefix("down_proj", prefix),
)
if hidden_act != "silu":
raise ValueError(
f"Unsupported activation: {hidden_act}. "
"Only silu is supported for now."
)
self.act_fn = SiluAndMul()
def forward(self, x):
gate_up, _ = self.gate_up_proj(x)
x = self.act_fn(gate_up)
x, _ = self.down_proj(x)
return x
class Qwen2Attention(nn.Module):
def __init__(
self,
hidden_size: int,
num_heads: int,
num_kv_heads: int,
head_dim: Optional[int] = None,
layer_id: int = 0,
rope_theta: float = 1000000,
rope_scaling: Optional[Dict[str, Any]] = None,
max_position_embeddings: int = 32768,
quant_config: Optional[QuantizationConfig] = None,
dual_chunk_attention_config: Optional[dict[str, Any]] = None,
prefix: str = "",
) -> None:
super().__init__()
self.hidden_size = hidden_size
tp_size = get_tensor_model_parallel_world_size()
self.total_num_heads = num_heads
assert self.total_num_heads % tp_size == 0
self.num_heads = self.total_num_heads // tp_size
self.total_num_kv_heads = num_kv_heads
if self.total_num_kv_heads >= tp_size:
# Number of KV heads is greater than TP size, so we partition
# the KV heads across multiple tensor parallel GPUs.
assert self.total_num_kv_heads % tp_size == 0
else:
# Number of KV heads is less than TP size, so we replicate
# the KV heads across multiple tensor parallel GPUs.
assert tp_size % self.total_num_kv_heads == 0
self.num_kv_heads = max(1, self.total_num_kv_heads // tp_size)
if head_dim is not None:
self.head_dim = head_dim
else:
self.head_dim = hidden_size // self.total_num_heads
self.q_size = self.num_heads * self.head_dim
self.kv_size = self.num_kv_heads * self.head_dim
self.scaling = self.head_dim**-0.5
self.rope_theta = rope_theta
self.max_position_embeddings = max_position_embeddings
self.qkv_proj = QKVParallelLinear(
hidden_size,
self.head_dim,
self.total_num_heads,
self.total_num_kv_heads,
bias=True,
quant_config=quant_config,
prefix=add_prefix("qkv_proj", prefix),
)
self.o_proj = RowParallelLinear(
self.total_num_heads * self.head_dim,
hidden_size,
bias=False,
quant_config=quant_config,
prefix=add_prefix("o_proj", prefix),
)
self.rotary_emb = get_rope(
self.head_dim,
rotary_dim=self.head_dim,
max_position=max_position_embeddings,
base=rope_theta,
rope_scaling=rope_scaling,
dual_chunk_attention_config=dual_chunk_attention_config,
)
self.attn = RadixAttention(
self.num_heads,
self.head_dim,
self.scaling,
num_kv_heads=self.num_kv_heads,
layer_id=layer_id,
quant_config=quant_config,
prefix=add_prefix("attn", prefix),
)
def forward(
self,
positions: torch.Tensor,
hidden_states: torch.Tensor,
forward_batch: ForwardBatch,
) -> torch.Tensor:
qkv, _ = self.qkv_proj(hidden_states)
q, k, v = qkv.split([self.q_size, self.kv_size, self.kv_size], dim=-1)
q, k = self.rotary_emb(positions, q, k)
attn_output = self.attn(q, k, v, forward_batch)
output, _ = self.o_proj(attn_output)
return output
class Qwen2DecoderLayer(nn.Module):
def __init__(
self,
config: Qwen2Config,
layer_id: int = 0,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
alt_stream: Optional[torch.cuda.Stream] = None,
) -> None:
super().__init__()
self.hidden_size = config.hidden_size
rope_theta = getattr(config, "rope_theta", 1000000)
rope_scaling = getattr(config, "rope_scaling", None)
max_position_embeddings = getattr(config, "max_position_embeddings", 32768)
head_dim = getattr(config, "head_dim", None)
dual_chunk_attention_config = getattr(
config, "dual_chunk_attention_config", None
)
self.self_attn = Qwen2Attention(
hidden_size=self.hidden_size,
num_heads=config.num_attention_heads,
num_kv_heads=config.num_key_value_heads,
head_dim=head_dim,
layer_id=layer_id,
rope_theta=rope_theta,
rope_scaling=rope_scaling,
max_position_embeddings=max_position_embeddings,
quant_config=quant_config,
dual_chunk_attention_config=dual_chunk_attention_config,
prefix=add_prefix("self_attn", prefix),
)
self.mlp = Qwen2MLP(
hidden_size=self.hidden_size,
intermediate_size=config.intermediate_size,
hidden_act=config.hidden_act,
quant_config=quant_config,
prefix=add_prefix("mlp", prefix),
)
self.input_layernorm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
self.post_attention_layernorm = RMSNorm(
config.hidden_size, eps=config.rms_norm_eps
)
def forward(
self,
positions: torch.Tensor,
hidden_states: torch.Tensor,
forward_batch: ForwardBatch,
residual: Optional[torch.Tensor],
) -> Tuple[torch.Tensor, torch.Tensor]:
# Self Attention
if residual is None:
residual = hidden_states
hidden_states = self.input_layernorm(hidden_states)
else:
hidden_states, residual = self.input_layernorm(hidden_states, residual)
hidden_states = self.self_attn(
positions=positions,
hidden_states=hidden_states,
forward_batch=forward_batch,
)
# Fully Connected
hidden_states, residual = self.post_attention_layernorm(hidden_states, residual)
hidden_states = self.mlp(hidden_states)
return hidden_states, residual
class Qwen2Model(nn.Module):
def __init__(
self,
config: Qwen2Config,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
decoder_layer_type: type[nn.Module] = Qwen2DecoderLayer,
alt_stream: Optional[torch.cuda.Stream] = None,
) -> None:
super().__init__()
self.config = config
self.padding_idx = config.pad_token_id
self.vocab_size = config.vocab_size
self.pp_group = get_pp_group()
if self.pp_group.is_first_rank:
self.embed_tokens = VocabParallelEmbedding(
config.vocab_size,
config.hidden_size,
quant_config=quant_config,
enable_tp=not global_server_args_dict["enable_dp_attention"],
prefix=add_prefix("embed_tokens", prefix),
)
else:
self.embed_tokens = PPMissingLayer()
# Use the provided decoder layer type or default to Qwen2DecoderLayer
decoder_layer_type = decoder_layer_type or Qwen2DecoderLayer
self.layers, self.start_layer, self.end_layer = make_layers(
config.num_hidden_layers,
lambda idx, prefix: decoder_layer_type(
layer_id=idx,
config=config,
quant_config=quant_config,
prefix=prefix,
alt_stream=alt_stream,
),
pp_rank=self.pp_group.rank_in_group,
pp_size=self.pp_group.world_size,
prefix=add_prefix("layers", prefix),
)
if self.pp_group.is_last_rank:
self.norm = RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
else:
self.norm = PPMissingLayer(return_tuple=True)
# For EAGLE3 support
self.layers_to_capture = []
def get_input_embedding(self, input_ids: torch.Tensor) -> torch.Tensor:
if hasattr(self.config, "scale_emb"):
return self.get_input_embeddings()(input_ids) * self.config.scale_emb
else:
return self.get_input_embeddings()(input_ids)
def get_input_embeddings(self) -> nn.Embedding:
return self.embed_tokens
def forward(
self,
input_ids: torch.Tensor,
positions: torch.Tensor,
forward_batch: ForwardBatch,
input_embeds: torch.Tensor = None,
pp_proxy_tensors: Optional[PPProxyTensors] = None,
) -> Union[torch.Tensor, PPProxyTensors]:
if self.pp_group.is_first_rank:
if input_embeds is None:
hidden_states = self.embed_tokens(input_ids)
else:
hidden_states = input_embeds
residual = None
else:
assert pp_proxy_tensors is not None
hidden_states = pp_proxy_tensors["hidden_states"]
residual = pp_proxy_tensors["residual"]
aux_hidden_states = []
for i in range(self.start_layer, self.end_layer):
if i in self.layers_to_capture:
aux_hidden_states.append(
hidden_states + residual if residual is not None else hidden_states
)
layer = self.layers[i]
hidden_states, residual = layer(
positions,
hidden_states,
forward_batch,
residual,
)
if not self.pp_group.is_last_rank:
return PPProxyTensors(
{
"hidden_states": hidden_states,
"residual": residual,
}
)
else:
if hidden_states.shape[0] != 0:
if residual is None:
hidden_states = self.norm(hidden_states)
else:
hidden_states, _ = self.norm(hidden_states, residual)
if len(aux_hidden_states) == 0:
return hidden_states
return hidden_states, aux_hidden_states
# If this function is called, it should always initialize KV cache scale
# factors (or else raise an exception). Thus, handled exceptions should
# make sure to leave KV cache scale factors in a known good (dummy) state
def load_kv_cache_scales(self, quantization_param_path: str) -> None:
tp_size = get_tensor_model_parallel_world_size()
tp_rank = get_tensor_model_parallel_rank()
for layer_idx, scaling_factor in kv_cache_scales_loader(
quantization_param_path,
tp_rank,
tp_size,
self.config.num_hidden_layers,
self.config.__class__.model_type,
):
if not isinstance(self.layers[layer_idx], nn.Identity):
layer_self_attn = self.layers[layer_idx].self_attn
if hasattr(layer_self_attn.attn, "k_scale"):
layer_self_attn.attn.k_scale = scaling_factor
layer_self_attn.attn.v_scale = scaling_factor
else:
raise RuntimeError(
"Self attention has no KV cache scaling " "factor attribute!"
)
class Qwen2ForCausalLM(nn.Module):
# BitandBytes specific attributes
default_bitsandbytes_target_modules = [
".gate_proj.",
".down_proj.",
".up_proj.",
".q_proj.",
".k_proj.",
".v_proj.",
".o_proj.",
]
bitsandbytes_stacked_params_mapping = {
# shard_name, weight_name, index
"q_proj": ("qkv_proj", 0),
"k_proj": ("qkv_proj", 1),
"v_proj": ("qkv_proj", 2),
"gate_proj": ("gate_up_proj", 0),
"up_proj": ("gate_up_proj", 1),
}
def __init__(
self,
config: Qwen2Config,
quant_config: Optional[QuantizationConfig] = None,
prefix: str = "",
) -> None:
super().__init__()
self.pp_group = get_pp_group()
self.config = config
self.quant_config = quant_config
self.model = Qwen2Model(
config, quant_config=quant_config, prefix=add_prefix("model", prefix)
)
self.capture_aux_hidden_states = False
# handle the lm head on different pp ranks
if self.pp_group.is_last_rank:
if self.pp_group.world_size == 1 and config.tie_word_embeddings:
self.lm_head = self.model.embed_tokens
else:
self.lm_head = ParallelLMHead(
config.vocab_size,
config.hidden_size,
quant_config=quant_config,
prefix=add_prefix("lm_head", prefix),
)
else:
# ranks other than the last rank will have a placeholder layer
self.lm_head = PPMissingLayer()
# perform weight tying for PP
if self.pp_group.world_size > 1 and config.tie_word_embeddings:
if self.pp_group.is_first_rank:
self.pp_group.send(
self.model.embed_tokens.weight, dst=self.pp_group.last_rank
)
else:
emb_token_weight = self.pp_group.recv(
size=(config.vocab_size, config.hidden_size),
dtype=next(self.model.parameters()).dtype,
src=self.pp_group.first_rank,
)
self.lm_head.weight.copy_(emb_token_weight)
self.logits_processor = LogitsProcessor(config)
self.pooler = Pooler(pooling_type=PoolingType.LAST, normalize=True)
def get_input_embedding(self, input_ids: torch.Tensor) -> torch.Tensor:
return self.model.get_input_embedding(input_ids)
def get_input_embeddings(self) -> nn.Embedding:
return self.model.embed_tokens
@torch.no_grad()
def forward(
self,
input_ids: torch.Tensor,
positions: torch.Tensor,
forward_batch: ForwardBatch,
input_embeds: torch.Tensor = None,
get_embedding: bool = False,
pp_proxy_tensors: Optional[PPProxyTensors] = None,
) -> torch.Tensor:
hidden_states = self.model(
input_ids,
positions,
forward_batch,
input_embeds,
pp_proxy_tensors=pp_proxy_tensors,
)
aux_hidden_states = None
if self.capture_aux_hidden_states:
hidden_states, aux_hidden_states = hidden_states
if self.pp_group.is_last_rank:
if not get_embedding:
return self.logits_processor(
input_ids, hidden_states, self.lm_head, forward_batch, aux_hidden_states
)
else:
return self.pooler(hidden_states, forward_batch)
else:
return hidden_states
@torch.no_grad()
def forward_split_prefill(
self,
input_ids: torch.Tensor,
positions: torch.Tensor,
forward_batch: ForwardBatch,
split_interval: Tuple[int, int], # [start, end) 0-based
input_embeds: torch.Tensor = None,
):
start, end = split_interval
# embed
if start == 0:
if input_embeds is None:
forward_batch.hidden_states = self.model.embed_tokens(input_ids)
else:
forward_batch.hidden_states = input_embeds
# decoder layer
for i in range(start, end):
layer = self.model.layers[i]
forward_batch.hidden_states, forward_batch.residual = layer(
positions,
forward_batch.hidden_states,
forward_batch,
forward_batch.residual,
)
if end == self.model.config.num_hidden_layers:
# norm
hidden_states, _ = self.model.norm(
forward_batch.hidden_states, forward_batch.residual
)
forward_batch.hidden_states = hidden_states
# logits process
result = self.logits_processor(
input_ids, forward_batch.hidden_states, self.lm_head, forward_batch
)
else:
result = None
return result
@property
def start_layer(self):
return self.model.start_layer
@property
def end_layer(self):
return self.model.end_layer
def load_weights(self, weights: Iterable[Tuple[str, torch.Tensor]]):
stacked_params_mapping = [
# (param_name, shard_name, shard_id)
("qkv_proj", "q_proj", "q"),
("qkv_proj", "k_proj", "k"),
("qkv_proj", "v_proj", "v"),
("gate_up_proj", "gate_proj", 0),
("gate_up_proj", "up_proj", 1),
]
params_dict = dict(self.named_parameters())
for name, loaded_weight in weights:
layer_id = get_layer_id(name)
if (
layer_id is not None
and hasattr(self.model, "start_layer")
and (
layer_id < self.model.start_layer
or layer_id >= self.model.end_layer
)
):
continue
if "rotary_emb.inv_freq" in name or "projector" in name:
continue
if "rotary_emb.cos_cached" in name or "rotary_emb.sin_cached" in name:
# Models trained using ColossalAI may include these tensors in
# the checkpoint. Skip them.
continue
if self.config.tie_word_embeddings and "lm_head.weight" in name:
if self.pp_group.world_size > 1 and self.pp_group.is_last_rank:
# Handle pp weight tying here
# find the embed_tokens.weight in the weights
embed_token_weights = next(
filter(lambda x: x[0] == "model.embed_tokens.weight", weights)
)[1]
loaded_weight = embed_token_weights
else:
continue
if name.startswith("model.vision_tower") and name not in params_dict:
continue
for param_name, weight_name, shard_id in stacked_params_mapping:
if weight_name not in name:
continue
name = name.replace(weight_name, param_name)
# Skip loading extra bias for GPTQ models.
if name.endswith(".bias") and name not in params_dict:
continue
if name not in params_dict:
continue
param = params_dict[name]
weight_loader = param.weight_loader
weight_loader(param, loaded_weight, shard_id)
break
else:
# Skip loading extra bias for GPTQ models.
if name.endswith(".bias") and name not in params_dict:
continue
if name in params_dict.keys():
param = params_dict[name]
weight_loader = getattr(
param, "weight_loader", default_weight_loader
)
weight_loader(param, loaded_weight)
else:
logger.warning(f"Parameter {name} not found in params_dict")
def get_embed_and_head(self):
return self.model.embed_tokens.weight, self.lm_head.weight
def set_embed_and_head(self, embed, head):
del self.model.embed_tokens.weight
del self.lm_head.weight
self.model.embed_tokens.weight = embed
self.lm_head.weight = head
torch.cuda.empty_cache()
torch.cuda.synchronize()
def load_kv_cache_scales(self, quantization_param_path: str) -> None:
self.model.load_kv_cache_scales(quantization_param_path)
def set_eagle3_layers_to_capture(self, layer_ids: Optional[List[int]] = None):
if not self.pp_group.is_last_rank:
return
self.capture_aux_hidden_states = True
if layer_ids is None:
num_layers = self.config.num_hidden_layers
self.model.layers_to_capture = [
2,
num_layers // 2,
num_layers - 3,
] # Specific layers for EAGLE3 support
else:
self.model.layers_to_capture = [val + 1 for val in layer_ids]
EntryClass = Qwen2ForCausalLM

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.51.3"
}

BIN
merges.txt (Stored with Git LFS) Normal file
View File

Binary file not shown.

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1963a73fe18d28e4cc7933c106599202f57a9e78f7b34ff7cdba463512d77d8c
size 4960142856

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:464ef6d2595f2c385002554fcaf076446bdb389f5bba9aabef52b8d4dae23748
size 4998217992

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea4a19e13f23d0edade92235785164c85eb08e5d5dc85cb001eba070a50a8372
size 4965322672

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:99e7e79337525b3df05c3d3fdbf467a467ae97d9730e42c068068397fbbf9b1c
size 4420301592

2122
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

12
quantize_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"bits": 4,
"group_size": 128,
"sym": true,
"data_type": "int",
"nsamples": 512,
"autoround_version": "0.5.1",
"quant_method": "gptq",
"desc_act": false,
"true_sequential": false,
"damp_percent": 0.01
}

31
special_tokens_map.json Normal file
View 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
}
}

BIN
tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

240
tokenizer_config.json Normal file
View File

@@ -0,0 +1,240 @@
{
"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
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"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\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\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.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\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 {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if thinking_mode is defined %}\n {%- if thinking_mode == \"on\" %}\n {{- '<think>\\n' }}\n {%- elif thinking_mode == \"off\" %}\n {{- '<think>\\n\\n' }}\n {%- endif %}\n {%- endif %}\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
}

BIN
vocab.json (Stored with Git LFS) Normal file
View File

Binary file not shown.