MPWARE commited on
Commit
c9a02ef
·
verified ·
1 Parent(s): 0d6c5d7

Upload Qwen2ForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/DeepSeek-R1-Distill-Qwen-14B-BnB-4bits",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 131072,
14
+ "max_window_layers": 48,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "_load_in_4bit": true,
21
+ "_load_in_8bit": false,
22
+ "bnb_4bit_compute_dtype": "float32",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": true,
31
+ "load_in_8bit": false,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-05,
35
+ "rope_scaling": null,
36
+ "rope_theta": 1000000.0,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.48.3",
41
+ "use_cache": true,
42
+ "use_sliding_window": false,
43
+ "vocab_size": 152064
44
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151646,
4
+ "do_sample": true,
5
+ "eos_token_id": 151643,
6
+ "temperature": 0.6,
7
+ "top_p": 0.95,
8
+ "transformers_version": "4.48.3"
9
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51332a60a8f8d5dbb22c898e9bbeea5c3131e62c0b1131311ffd830d050b5530
3
+ size 4999650880
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3345cb05e323b91a0cf2e7dfa562dd05ea15b124b87da534a80d7a34ff0133
3
+ size 3991186824
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc8182780a9605acbd87edbfe360569962f73b65e0304c212c18ae6a3a9d899
3
+ size 1557135488
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff