bnjmnmarie commited on
Commit
ed705ce
·
verified ·
1 Parent(s): cc9c886

Upload Qwen2ForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "DeepSeek-R1-Distill-Qwen-14B-AutoRound-GPTQ-4bit",
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
+ "batch_size": 4,
21
+ "bits": 4,
22
+ "block_name_to_quantize": null,
23
+ "cache_block_outputs": true,
24
+ "damp_percent": 0.01,
25
+ "dataset": null,
26
+ "desc_act": false,
27
+ "exllama_config": {
28
+ "version": 1
29
+ },
30
+ "group_size": 128,
31
+ "max_input_length": null,
32
+ "model_seqlen": null,
33
+ "module_name_preceding_first_block": null,
34
+ "modules_in_block_to_quantize": null,
35
+ "pad_token_id": null,
36
+ "quant_method": "gptq",
37
+ "sym": true,
38
+ "tokenizer": null,
39
+ "true_sequential": false,
40
+ "use_cuda_fp16": false,
41
+ "use_exllama": true
42
+ },
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_scaling": null,
45
+ "rope_theta": 1000000.0,
46
+ "sliding_window": null,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "float16",
49
+ "transformers_version": "4.47.1",
50
+ "use_cache": true,
51
+ "use_sliding_window": false,
52
+ "vocab_size": 152064
53
+ }
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": "4.47.1"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a00e3f01edd82c9e4917d4aa41338c981463b3e80e553a4928cac4e08864dd88
3
+ size 4997121424
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b3b396a0387a9fcb184f5d3d920a07d1d30680cf3dcf23cf87d2d077f28130
3
+ size 4991638208
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff