singhshiva commited on
Commit
892d71d
1 Parent(s): c6c6ec8

Upload Qwen2ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +43 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/teamspace/studios/this_studio/quantized_model",
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": 2048,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 36,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "quantization_config": {
20
+ "backend": "autoawq",
21
+ "bits": 4,
22
+ "do_fuse": false,
23
+ "exllama_config": null,
24
+ "fuse_max_seq_len": null,
25
+ "group_size": 128,
26
+ "modules_to_fuse": null,
27
+ "modules_to_not_convert": null,
28
+ "quant_method": "awq",
29
+ "version": "gemm",
30
+ "zero_point": true
31
+ },
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_scaling": null,
34
+ "rope_theta": 1000000.0,
35
+ "sliding_window": null,
36
+ "tie_word_embeddings": true,
37
+ "torch_dtype": "float16",
38
+ "transformers_version": "4.46.1",
39
+ "use_cache": true,
40
+ "use_mrope": false,
41
+ "use_sliding_window": false,
42
+ "vocab_size": 151936
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 2048,
6
+ "transformers_version": "4.46.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f42a5c792babc9c1735bee6a6a0a35f2e9cdef834cf33420f0f4b318887f6ae2
3
+ size 2064374680