Upload RuQwen2ForCausalLM
Browse files- README.md +4 -4
- config.json +42 -0
- generation_config.json +14 -0
- model.safetensors +3 -0
README.md
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
language:
|
4 |
- ru
|
5 |
- en
|
6 |
-
base_model:
|
7 |
-
- Qwen/Qwen2.5-3B-Instruct
|
8 |
-
pipeline_tag: text-generation
|
9 |
library_name: transformers
|
|
|
|
|
10 |
---
|
11 |
|
12 |
---
|
|
|
1 |
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2.5-3B-Instruct
|
4 |
language:
|
5 |
- ru
|
6 |
- en
|
|
|
|
|
|
|
7 |
library_name: transformers
|
8 |
+
license: apache-2.0
|
9 |
+
pipeline_tag: text-generation
|
10 |
---
|
11 |
|
12 |
---
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/content/RuQwen2.5-3B-Instruct-AWQ",
|
3 |
+
"add_bias_to_lm_head": true,
|
4 |
+
"architectures": [
|
5 |
+
"RuQwen2ForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 121125,
|
9 |
+
"eos_token_id": 121127,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"max_window_layers": 70,
|
16 |
+
"model_type": "qwen2",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 36,
|
19 |
+
"num_key_value_heads": 2,
|
20 |
+
"quantization_config": {
|
21 |
+
"backend": "autoawq",
|
22 |
+
"bits": 4,
|
23 |
+
"do_fuse": false,
|
24 |
+
"exllama_config": null,
|
25 |
+
"fuse_max_seq_len": null,
|
26 |
+
"group_size": 128,
|
27 |
+
"modules_to_fuse": null,
|
28 |
+
"modules_to_not_convert": null,
|
29 |
+
"quant_method": "awq",
|
30 |
+
"version": "gemm",
|
31 |
+
"zero_point": true
|
32 |
+
},
|
33 |
+
"rms_norm_eps": 1e-06,
|
34 |
+
"rope_theta": 1000000.0,
|
35 |
+
"sliding_window": null,
|
36 |
+
"tie_word_embeddings": true,
|
37 |
+
"torch_dtype": "float16",
|
38 |
+
"transformers_version": "4.44.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"use_sliding_window": false,
|
41 |
+
"vocab_size": 121147
|
42 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 121125,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
121127,
|
6 |
+
121125
|
7 |
+
],
|
8 |
+
"pad_token_id": 121125,
|
9 |
+
"repetition_penalty": 1.05,
|
10 |
+
"temperature": 0.3,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.44.2"
|
14 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7b85ae72f79bc384edda75df9563e6c07ff607c82997cbb1617c50fe8350259
|
3 |
+
size 1938505318
|