Upload folder using huggingface_hub
Browse files- .gitattributes +3 -0
- README.md +201 -1
- Tcomanr-V2_1-4.0B-IQ4_NL.gguf +3 -0
- Tcomanr-V2_1-4.0B-Q8_0.gguf +3 -0
- config.json +30 -0
- mergekit_config.yml +41 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
.gitattributes
CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
Tcomanr-V2_1-4.0B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Tcomanr-V2_1-4.0B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,203 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- ertghiu256/qwen3-multi-reasoner
|
4 |
+
- ertghiu256/deepseek-r1-0528-distilled-qwen3
|
5 |
+
- huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
|
6 |
+
- ertghiu256/qwen3-4b-code-reasoning
|
7 |
+
- Qwen/Qwen3-4B-Thinking-2507
|
8 |
+
- ertghiu256/qwen3-math-reasoner
|
9 |
+
- POLARIS-Project/Polaris-4B-Preview
|
10 |
+
- Tesslate/UIGEN-T3-4B-Preview-MAX
|
11 |
+
- ertghiu256/Qwen3-Hermes-4b
|
12 |
+
- ertghiu256/qwen-3-4b-mixture-of-thought
|
13 |
+
- ValiantLabs/Qwen3-4B-ShiningValiant3
|
14 |
+
- ValiantLabs/Qwen3-4B-Esper3
|
15 |
+
library_name: transformers
|
16 |
+
tags:
|
17 |
+
- mergekit
|
18 |
+
- merge
|
19 |
+
- thinking
|
20 |
+
- think
|
21 |
+
- reasoning
|
22 |
+
- reason
|
23 |
+
- code
|
24 |
+
- math
|
25 |
+
- qwen
|
26 |
+
- qwen3
|
27 |
+
|
28 |
---
|
29 |
+
# Ties merged COde MAth aNd Reasoning model
|
30 |
+
|
31 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
32 |
+
|
33 |
+
## Merge Details
|
34 |
+
This model is a revision of the [ertghiu256/Qwen3-4b-tcomanr-merge-v2](https://huggingface.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2/)
|
35 |
+
|
36 |
+
This model aims to combine the code and math capabilities by merging Qwen 3 2507 with multiple Qwen 3 finetunes.
|
37 |
+
|
38 |
+
# How to run
|
39 |
+
You can run this model by using multiple interface choices
|
40 |
+
|
41 |
+
## Transformers
|
42 |
+
As the qwen team suggested to use
|
43 |
+
```python
|
44 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
45 |
+
|
46 |
+
model_name = "ertghiu256/Qwen3-4b-tcomanr-merge-v2.1"
|
47 |
+
|
48 |
+
# load the tokenizer and the model
|
49 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
50 |
+
model = AutoModelForCausalLM.from_pretrained(
|
51 |
+
model_name,
|
52 |
+
torch_dtype="auto",
|
53 |
+
device_map="auto"
|
54 |
+
)
|
55 |
+
|
56 |
+
# prepare the model input
|
57 |
+
prompt = "Give me a short introduction to large language model."
|
58 |
+
messages = [
|
59 |
+
{"role": "user", "content": prompt}
|
60 |
+
]
|
61 |
+
text = tokenizer.apply_chat_template(
|
62 |
+
messages,
|
63 |
+
tokenize=False,
|
64 |
+
add_generation_prompt=True,
|
65 |
+
)
|
66 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
67 |
+
|
68 |
+
# conduct text completion
|
69 |
+
generated_ids = model.generate(
|
70 |
+
**model_inputs,
|
71 |
+
max_new_tokens=32768
|
72 |
+
)
|
73 |
+
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
74 |
+
|
75 |
+
# parsing thinking content
|
76 |
+
try:
|
77 |
+
# rindex finding 151668 (</think>)
|
78 |
+
index = len(output_ids) - output_ids[::-1].index(151668)
|
79 |
+
except ValueError:
|
80 |
+
index = 0
|
81 |
+
|
82 |
+
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
|
83 |
+
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
|
84 |
+
|
85 |
+
print("thinking content:", thinking_content) # no opening <think> tag
|
86 |
+
print("content:", content)
|
87 |
+
```
|
88 |
+
|
89 |
+
## Vllm
|
90 |
+
Run this command
|
91 |
+
```bash
|
92 |
+
vllm serve ertghiu256/Qwen3-4b-tcomanr-merge-v2.1 --enable-reasoning --reasoning-parser deepseek_r1
|
93 |
+
```
|
94 |
+
|
95 |
+
## Sglang
|
96 |
+
Run this command
|
97 |
+
```bash
|
98 |
+
python -m sglang.launch_server --model-path ertghiu256/Qwen3-4b-tcomanr-merge-v2.1 --reasoning-parser deepseek-r1
|
99 |
+
```
|
100 |
+
|
101 |
+
## llama.cpp
|
102 |
+
Run this command
|
103 |
+
```bash
|
104 |
+
llama-server --hf-repo ertghiu256/Qwen3-4b-tcomanr-merge-v2.1
|
105 |
+
```
|
106 |
+
or
|
107 |
+
```bash
|
108 |
+
llama-cli --hf ertghiu256/Qwen3-4b-tcomanr-merge-v2.1
|
109 |
+
```
|
110 |
+
|
111 |
+
## Ollama
|
112 |
+
Run this command
|
113 |
+
```bash
|
114 |
+
ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.1:Q8_0
|
115 |
+
```
|
116 |
+
or
|
117 |
+
```bash
|
118 |
+
ollama run hf.co/ertghiu256/Qwen3-4b-tcomanr-merge-v2.1:IQ4_NL
|
119 |
+
```
|
120 |
+
|
121 |
+
## LM Studio
|
122 |
+
Search
|
123 |
+
```
|
124 |
+
ertghiu256/Qwen3-4b-tcomanr-merge-v2
|
125 |
+
```
|
126 |
+
in the lm studio model search list then download
|
127 |
+
|
128 |
+
### Recomended parameters
|
129 |
+
```
|
130 |
+
temp: 0.6
|
131 |
+
num_ctx: ≥8192
|
132 |
+
top_p: 0.95
|
133 |
+
top_k: 20
|
134 |
+
Repeat Penalty: 1.2
|
135 |
+
```
|
136 |
+
|
137 |
+
### Merge Method
|
138 |
+
|
139 |
+
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.
|
140 |
+
|
141 |
+
### Models Merged
|
142 |
+
|
143 |
+
The following models were included in the merge:
|
144 |
+
* [ertghiu256/qwen3-multi-reasoner](https://huggingface.co/ertghiu256/qwen3-multi-reasoner)
|
145 |
+
* [ertghiu256/deepseek-r1-0528-distilled-qwen3](https://huggingface.co/ertghiu256/deepseek-r1-0528-distilled-qwen3)
|
146 |
+
* [huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated](https://huggingface.co/huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated)
|
147 |
+
* [ertghiu256/qwen3-4b-code-reasoning](https://huggingface.co/ertghiu256/qwen3-4b-code-reasoning)
|
148 |
+
* [ertghiu256/qwen3-math-reasoner](https://huggingface.co/ertghiu256/qwen3-math-reasoner)
|
149 |
+
* [POLARIS-Project/Polaris-4B-Preview](https://huggingface.co/POLARIS-Project/Polaris-4B-Preview)
|
150 |
+
* [Tesslate/UIGEN-T3-4B-Preview-MAX](https://huggingface.co/Tesslate/UIGEN-T3-4B-Preview-MAX)
|
151 |
+
* [ertghiu256/Qwen3-Hermes-4b](https://huggingface.co/ertghiu256/Qwen3-Hermes-4b)
|
152 |
+
* [ertghiu256/qwen-3-4b-mixture-of-thought](https://huggingface.co/ertghiu256/qwen-3-4b-mixture-of-thought)
|
153 |
+
* [ValiantLabs/Qwen3-4B-ShiningValiant3](https://huggingface.co/ValiantLabs/Qwen3-4B-ShiningValiant3)
|
154 |
+
* [ValiantLabs/Qwen3-4B-Esper3](https://huggingface.co/ValiantLabs/Qwen3-4B-Esper3)
|
155 |
+
|
156 |
+
### Configuration
|
157 |
+
|
158 |
+
The following YAML configuration was used to produce this model:
|
159 |
+
|
160 |
+
```yaml
|
161 |
+
models:
|
162 |
+
- model: ertghiu256/qwen3-math-reasoner
|
163 |
+
parameters:
|
164 |
+
weight: 0.8
|
165 |
+
- model: ertghiu256/qwen3-4b-code-reasoning
|
166 |
+
parameters:
|
167 |
+
weight: 0.9
|
168 |
+
- model: ertghiu256/qwen-3-4b-mixture-of-thought
|
169 |
+
parameters:
|
170 |
+
weight: 0.9
|
171 |
+
- model: POLARIS-Project/Polaris-4B-Preview
|
172 |
+
parameters:
|
173 |
+
weight: 0.9
|
174 |
+
- model: ertghiu256/qwen3-multi-reasoner
|
175 |
+
parameters:
|
176 |
+
weight: 0.8
|
177 |
+
- model: ertghiu256/Qwen3-Hermes-4b
|
178 |
+
parameters:
|
179 |
+
weight: 0.8
|
180 |
+
- model: ValiantLabs/Qwen3-4B-Esper3
|
181 |
+
parameters:
|
182 |
+
weight: 0.8
|
183 |
+
- model: Tesslate/UIGEN-T3-4B-Preview-MAX
|
184 |
+
parameters:
|
185 |
+
weight: 0.9
|
186 |
+
- model: ValiantLabs/Qwen3-4B-ShiningValiant3
|
187 |
+
parameters:
|
188 |
+
weight: 0.6
|
189 |
+
- model: ertghiu256/deepseek-r1-0528-distilled-qwen3
|
190 |
+
parameters:
|
191 |
+
weight: 0.1
|
192 |
+
- model: huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
|
193 |
+
parameters:
|
194 |
+
weight: 0.6
|
195 |
+
merge_method: ties
|
196 |
+
base_model: Qwen/Qwen3-4B-Thinking-2507
|
197 |
+
parameters:
|
198 |
+
normalize: true
|
199 |
+
int8_mask: true
|
200 |
+
lambda: 1.0
|
201 |
+
dtype: float16
|
202 |
+
|
203 |
+
```
|
Tcomanr-V2_1-4.0B-IQ4_NL.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9da5810db81be876d9075ccaee04de0014557960a1030a9ec82376f7c1e7ba32
|
3 |
+
size 2393797728
|
Tcomanr-V2_1-4.0B-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:479aeed8ee5a41f1d35cd260fb20d8bbf42f67b9b75d992ac9e639df32aa93f1
|
3 |
+
size 4280407648
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen3ForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2560,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 9728,
|
14 |
+
"max_position_embeddings": 262144,
|
15 |
+
"max_window_layers": 36,
|
16 |
+
"model_type": "qwen3",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 36,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 5000000,
|
23 |
+
"sliding_window": null,
|
24 |
+
"tie_word_embeddings": true,
|
25 |
+
"torch_dtype": "float16",
|
26 |
+
"transformers_version": "4.51.3",
|
27 |
+
"use_cache": true,
|
28 |
+
"use_sliding_window": false,
|
29 |
+
"vocab_size": 151936
|
30 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: ertghiu256/qwen3-math-reasoner
|
3 |
+
parameters:
|
4 |
+
weight: 0.8
|
5 |
+
- model: ertghiu256/qwen3-4b-code-reasoning
|
6 |
+
parameters:
|
7 |
+
weight: 0.9
|
8 |
+
- model: ertghiu256/qwen-3-4b-mixture-of-thought
|
9 |
+
parameters:
|
10 |
+
weight: 0.9
|
11 |
+
- model: POLARIS-Project/Polaris-4B-Preview
|
12 |
+
parameters:
|
13 |
+
weight: 0.9
|
14 |
+
- model: ertghiu256/qwen3-multi-reasoner
|
15 |
+
parameters:
|
16 |
+
weight: 0.8
|
17 |
+
- model: ertghiu256/Qwen3-Hermes-4b
|
18 |
+
parameters:
|
19 |
+
weight: 0.8
|
20 |
+
- model: ValiantLabs/Qwen3-4B-Esper3
|
21 |
+
parameters:
|
22 |
+
weight: 0.8
|
23 |
+
- model: Tesslate/UIGEN-T3-4B-Preview-MAX
|
24 |
+
parameters:
|
25 |
+
weight: 0.9
|
26 |
+
- model: ValiantLabs/Qwen3-4B-ShiningValiant3
|
27 |
+
parameters:
|
28 |
+
weight: 0.6
|
29 |
+
- model: ertghiu256/deepseek-r1-0528-distilled-qwen3
|
30 |
+
parameters:
|
31 |
+
weight: 0.1
|
32 |
+
- model: huihui-ai/Huihui-Qwen3-4B-Thinking-2507-abliterated
|
33 |
+
parameters:
|
34 |
+
weight: 0.6
|
35 |
+
merge_method: ties
|
36 |
+
base_model: Qwen/Qwen3-4B-Thinking-2507
|
37 |
+
parameters:
|
38 |
+
normalize: true
|
39 |
+
int8_mask: true
|
40 |
+
lambda: 1.0
|
41 |
+
dtype: float16
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3225968174c867b9c76b303a5f9261f0c08f871fb6322276cb134b6d60573f57
|
3 |
+
size 4990818520
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1ca5311b84b798a37206facacb1a7101ff12749d7d520e96893d023f6dd783b
|
3 |
+
size 3054163080
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors"}}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
3 |
+
size 11422654
|
tokenizer_config.json
ADDED
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"151646": {
|
29 |
+
"content": "<|object_ref_start|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "<|object_ref_end|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "<|box_start|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "<|box_end|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "<|quad_start|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "<|quad_end|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "<|vision_start|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "<|vision_end|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "<|vision_pad|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "<|image_pad|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "<|video_pad|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"151657": {
|
117 |
+
"content": "<tool_call>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"151658": {
|
125 |
+
"content": "</tool_call>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"151659": {
|
133 |
+
"content": "<|fim_prefix|>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"151660": {
|
141 |
+
"content": "<|fim_middle|>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"151661": {
|
149 |
+
"content": "<|fim_suffix|>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"151662": {
|
157 |
+
"content": "<|fim_pad|>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"151663": {
|
165 |
+
"content": "<|repo_name|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"151664": {
|
173 |
+
"content": "<|file_sep|>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"151665": {
|
181 |
+
"content": "<tool_response>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"151666": {
|
189 |
+
"content": "</tool_response>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"151667": {
|
197 |
+
"content": "<think>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"151668": {
|
205 |
+
"content": "</think>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
}
|
212 |
+
},
|
213 |
+
"additional_special_tokens": [
|
214 |
+
"<|im_start|>",
|
215 |
+
"<|im_end|>",
|
216 |
+
"<|object_ref_start|>",
|
217 |
+
"<|object_ref_end|>",
|
218 |
+
"<|box_start|>",
|
219 |
+
"<|box_end|>",
|
220 |
+
"<|quad_start|>",
|
221 |
+
"<|quad_end|>",
|
222 |
+
"<|vision_start|>",
|
223 |
+
"<|vision_end|>",
|
224 |
+
"<|vision_pad|>",
|
225 |
+
"<|image_pad|>",
|
226 |
+
"<|video_pad|>"
|
227 |
+
],
|
228 |
+
"bos_token": null,
|
229 |
+
"chat_template": "{%- 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 %}",
|
230 |
+
"clean_up_tokenization_spaces": false,
|
231 |
+
"eos_token": "<|im_end|>",
|
232 |
+
"errors": "replace",
|
233 |
+
"model_max_length": 262144,
|
234 |
+
"pad_token": "<|endoftext|>",
|
235 |
+
"split_special_tokens": false,
|
236 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
237 |
+
"unk_token": null,
|
238 |
+
"add_bos_token": false
|
239 |
+
}
|