初始化项目，由ModelHub XC社区提供模型
Model: ertghiu256/Qwen3-4b-tcomanr-merge-v2.2 Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
*.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
|
||||||
|
Tcomanr-V2_2-4.0B-F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Tcomanr-V2_2-4.0B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
Tcomanr-V2_2-4.0B-Q8_0.gguf 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 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
|
||||||
|
- Tesslate/UIGEN-T3-4B-Preview-MAX
|
||||||
|
- ValiantLabs/Qwen3-4B-Esper3
|
||||||
|
- ValiantLabs/Qwen3-4B-ShiningValiant3
|
||||||
|
- ertghiu256/Qwen3-Hermes-4b
|
||||||
|
- ertghiu256/qwen3-math-reasoner
|
||||||
|
- ertghiu256/deepseek-r1-0528-distilled-qwen3
|
||||||
|
- ertghiu256/qwen-3-4b-mixture-of-thought
|
||||||
|
- Qwen/Qwen3-4B-Thinking-2507
|
||||||
|
- POLARIS-Project/Polaris-4B-Preview
|
||||||
|
- ertghiu256/qwen3-multi-reasoner
|
||||||
|
- ertghiu256/qwen3-4b-code-reasoning
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- mergekit
|
||||||
|
- merge
|
||||||
|
- thinking
|
||||||
|
- think
|
||||||
|
- reasoning
|
||||||
|
- reason
|
||||||
|
- code
|
||||||
|
- math
|
||||||
|
- qwen
|
||||||
|
- qwen3
|
||||||
|
new_version: ertghiu256/Qwen3-4b-tcomanr-merge-v2.3
|
||||||
|
---
|
||||||
|
# Ties merged COde MAth aNd Reasoning model
|
||||||
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||||
|
|
||||||
|
## Merge Details
|
||||||
|
This model is a revision of the [ertghiu256/Qwen3-4b-tcomanr-merge-v2](https://huggingface.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2/)
|
||||||
|
|
||||||
|
This model aims to combine the code and math capabilities by merging Qwen 3 2507 with multiple Qwen 3 finetunes.
|
||||||
|
|
||||||
|
# How to run
|
||||||
|
You can run this model by using multiple interface choices
|
||||||
|
|
||||||
|
## Transformers
|
||||||
|
As the qwen team suggested to use
|
||||||
|
```python
|
||||||
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_name = "ertghiu256/Qwen3-4b-tcomanr-merge-v2.2"
|
||||||
|
|
||||||
|
# load the tokenizer and the model
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(
|
||||||
|
model_name,
|
||||||
|
torch_dtype="auto",
|
||||||
|
device_map="auto"
|
||||||
|
)
|
||||||
|
|
||||||
|
# prepare the model input
|
||||||
|
prompt = "Give me a short introduction to large language model."
|
||||||
|
messages = [
|
||||||
|
{"role": "user", "content": prompt}
|
||||||
|
]
|
||||||
|
text = tokenizer.apply_chat_template(
|
||||||
|
messages,
|
||||||
|
tokenize=False,
|
||||||
|
add_generation_prompt=True,
|
||||||
|
)
|
||||||
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
||||||
|
|
||||||
|
# conduct text completion
|
||||||
|
generated_ids = model.generate(
|
||||||
|
**model_inputs,
|
||||||
|
max_new_tokens=32768
|
||||||
|
)
|
||||||
|
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
||||||
|
|
||||||
|
# parsing thinking content
|
||||||
|
try:
|
||||||
|
# rindex finding 151668 (</think>)
|
||||||
|
index = len(output_ids) - output_ids[::-1].index(151668)
|
||||||
|
except ValueError:
|
||||||
|
index = 0
|
||||||
|
|
||||||
|
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
|
||||||
|
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
|
||||||
|
|
||||||
|
print("thinking content:", thinking_content) # no opening <think> tag
|
||||||
|
print("content:", content)
|
||||||
|
```
|
||||||
|
|
||||||
|
## Vllm
|
||||||
|
Run this command
|
||||||
|
```bash
|
||||||
|
vllm serve ertghiu256/Qwen3-4b-tcomanr-merge-v2.2 --enable-reasoning --reasoning-parser deepseek_r1
|
||||||
|
```
|
||||||
|
|
||||||
|
## Sglang
|
||||||
|
Run this command
|
||||||
|
```bash
|
||||||
|
python -m sglang.launch_server --model-path ertghiu256/Qwen3-4b-tcomanr-merge-v2.2 --reasoning-parser deepseek-r1
|
||||||
|
```
|
||||||
|
|
||||||
|
## llama.cpp
|
||||||
|
Run this command
|
||||||
|
```bash
|
||||||
|
llama-server --hf-repo ertghiu256/Qwen3-4b-tcomanr-merge-v2.2
|
||||||
|
```
|
||||||
|
or
|
||||||
|
```bash
|
||||||
|
llama-cli --hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.2
|
||||||
|
```
|
||||||
|
|
||||||
|
## Ollama
|
||||||
|
Run this command
|
||||||
|
```bash
|
||||||
|
ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.2:Q8_0
|
||||||
|
```
|
||||||
|
or
|
||||||
|
```bash
|
||||||
|
ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.2:Q5_K_M
|
||||||
|
```
|
||||||
|
|
||||||
|
## LM Studio
|
||||||
|
Search
|
||||||
|
```
|
||||||
|
ertghiu256/Qwen3-4b-tcomanr-merge-v2.2
|
||||||
|
```
|
||||||
|
in the lm studio model search list then download
|
||||||
|
|
||||||
|
### Recomended parameters
|
||||||
|
```
|
||||||
|
temp: 0.7
|
||||||
|
num_ctx: ≥8192
|
||||||
|
top_p: 0.95
|
||||||
|
top_k: 40
|
||||||
|
Repeat Penalty: 1.1
|
||||||
|
```
|
||||||
|
|
||||||
|
### Merge Method
|
||||||
|
|
||||||
|
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen3-4B-Thinking-2507](https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507) as a base.
|
||||||
|
|
||||||
|
### Models Merged
|
||||||
|
|
||||||
|
The following models were included in the merge:
|
||||||
|
* [huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated)
|
||||||
|
* [Tesslate/UIGEN-T3-4B-Preview-MAX](https://huggingface.co/Tesslate/UIGEN-T3-4B-Preview-MAX)
|
||||||
|
* [ValiantLabs/Qwen3-4B-Esper3](https://huggingface.co/ValiantLabs/Qwen3-4B-Esper3)
|
||||||
|
* [ValiantLabs/Qwen3-4B-ShiningValiant3](https://huggingface.co/ValiantLabs/Qwen3-4B-ShiningValiant3)
|
||||||
|
* [ertghiu256/Qwen3-Hermes-4b](https://huggingface.co/ertghiu256/Qwen3-Hermes-4b)
|
||||||
|
* [ertghiu256/qwen3-math-reasoner](https://huggingface.co/ertghiu256/qwen3-math-reasoner)
|
||||||
|
* [ertghiu256/deepseek-r1-0528-distilled-qwen3](https://huggingface.co/ertghiu256/deepseek-r1-0528-distilled-qwen3)
|
||||||
|
* [ertghiu256/qwen-3-4b-mixture-of-thought](https://huggingface.co/ertghiu256/qwen-3-4b-mixture-of-thought)
|
||||||
|
* [POLARIS-Project/Polaris-4B-Preview](https://huggingface.co/POLARIS-Project/Polaris-4B-Preview)
|
||||||
|
* [ertghiu256/qwen3-multi-reasoner](https://huggingface.co/ertghiu256/qwen3-multi-reasoner)
|
||||||
|
* [ertghiu256/qwen3-4b-code-reasoning](https://huggingface.co/ertghiu256/qwen3-4b-code-reasoning)
|
||||||
|
|
||||||
|
### Configuration
|
||||||
|
|
||||||
|
The following YAML configuration was used to produce this model:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
models:
|
||||||
|
- model: ertghiu256/qwen3-math-reasoner
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: ertghiu256/qwen3-4b-code-reasoning
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: ertghiu256/qwen-3-4b-mixture-of-thought
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: POLARIS-Project/Polaris-4B-Preview
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: ertghiu256/qwen3-multi-reasoner
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: ertghiu256/Qwen3-Hermes-4b
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: ValiantLabs/Qwen3-4B-Esper3
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: Tesslate/UIGEN-T3-4B-Preview-MAX
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: ValiantLabs/Qwen3-4B-ShiningValiant3
|
||||||
|
parameters:
|
||||||
|
weight: 0.6
|
||||||
|
- model: ertghiu256/deepseek-r1-0528-distilled-qwen3
|
||||||
|
parameters:
|
||||||
|
weight: 0.1
|
||||||
|
- model: huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
|
||||||
|
parameters:
|
||||||
|
weight: 0.6
|
||||||
|
- model: Qwen/Qwen3-4B-Thinking-2507
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
merge_method: ties
|
||||||
|
base_model: Qwen/Qwen3-4B-Thinking-2507
|
||||||
|
parameters:
|
||||||
|
normalize: true
|
||||||
|
int8_mask: true
|
||||||
|
lambda: 1.0
|
||||||
|
dtype: float16
|
||||||
|
|
||||||
|
```
|
||||||
3
Tcomanr-V2_2-4.0B-F16.gguf
Normal file
3
Tcomanr-V2_2-4.0B-F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:dad136848b4e5f1a00d5662d22f000ca39ef133ae648f3c7d3f8c6d1c9c1d334
|
||||||
|
size 8051287648
|
||||||
3
Tcomanr-V2_2-4.0B-Q5_K_M.gguf
Normal file
3
Tcomanr-V2_2-4.0B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:77832e36d59418ad75b1792bf2838c3863e74833b5ccf7a7b30f508e27566f43
|
||||||
|
size 2889516128
|
||||||
3
Tcomanr-V2_2-4.0B-Q8_0.gguf
Normal file
3
Tcomanr-V2_2-4.0B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c36796717e5d578b898cccdca65993625fffcec6348d854d82d8609668caded3
|
||||||
|
size 4280407648
|
||||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 2560,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 9728,
|
||||||
|
"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",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention",
|
||||||
|
"full_attention"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 262144,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 5000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.55.4",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
44
mergekit_config.yml
Normal file
44
mergekit_config.yml
Normal file
@@ -0,0 +1,44 @@
|
|||||||
|
models:
|
||||||
|
- model: ertghiu256/qwen3-math-reasoner
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: ertghiu256/qwen3-4b-code-reasoning
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: ertghiu256/qwen-3-4b-mixture-of-thought
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: POLARIS-Project/Polaris-4B-Preview
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: ertghiu256/qwen3-multi-reasoner
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: ertghiu256/Qwen3-Hermes-4b
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: ValiantLabs/Qwen3-4B-Esper3
|
||||||
|
parameters:
|
||||||
|
weight: 0.8
|
||||||
|
- model: Tesslate/UIGEN-T3-4B-Preview-MAX
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
- model: ValiantLabs/Qwen3-4B-ShiningValiant3
|
||||||
|
parameters:
|
||||||
|
weight: 0.6
|
||||||
|
- model: ertghiu256/deepseek-r1-0528-distilled-qwen3
|
||||||
|
parameters:
|
||||||
|
weight: 0.1
|
||||||
|
- model: huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
|
||||||
|
parameters:
|
||||||
|
weight: 0.6
|
||||||
|
- model: Qwen/Qwen3-4B-Thinking-2507
|
||||||
|
parameters:
|
||||||
|
weight: 0.9
|
||||||
|
merge_method: ties
|
||||||
|
base_model: Qwen/Qwen3-4B-Thinking-2507
|
||||||
|
parameters:
|
||||||
|
normalize: true
|
||||||
|
int8_mask: true
|
||||||
|
lambda: 1.0
|
||||||
|
dtype: float16
|
||||||
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3225968174c867b9c76b303a5f9261f0c08f871fb6322276cb134b6d60573f57
|
||||||
|
size 4990818520
|
||||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c1ca5311b84b798a37206facacb1a7101ff12749d7d520e96893d023f6dd783b
|
||||||
|
size 3054163080
|
||||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||||
|
size 11422654
|
||||||
239
tokenizer_config.json
Normal file
239
tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
|||||||
|
{
|
||||||
|
"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 message.content is string 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.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\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 {{- 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<think>\\n' }}\n{%- endif %}",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 262144,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null,
|
||||||
|
"add_bos_token": false
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user