ybelkada HF staff commited on
Commit
d1d5cc4
1 Parent(s): 3322bcd

Upload CohereForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CohereForAI/c4ai-command-r-v01",
3
+ "architectures": [
4
+ "CohereForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "CohereForAI/c4ai-command-r-v01--configuration_cohere.CohereConfig",
10
+ "AutoModel": "CohereForAI/c4ai-command-r-v01--modeling_cohere.CohereModel",
11
+ "AutoModelForCausalLM": "CohereForAI/c4ai-command-r-v01--modeling_cohere.CohereForCausalLM"
12
+ },
13
+ "bos_token_id": 5,
14
+ "eos_token_id": 255001,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 8192,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 22528,
19
+ "layer_norm_eps": 1e-05,
20
+ "logit_scale": 0.0625,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "cohere",
23
+ "num_attention_heads": 64,
24
+ "num_hidden_layers": 40,
25
+ "num_key_value_heads": 64,
26
+ "pad_token_id": 0,
27
+ "pretraining_tp": 1,
28
+ "quantization_config": {
29
+ "_load_in_4bit": true,
30
+ "_load_in_8bit": false,
31
+ "bnb_4bit_compute_dtype": "float32",
32
+ "bnb_4bit_quant_storage": "uint8",
33
+ "bnb_4bit_quant_type": "fp4",
34
+ "bnb_4bit_use_double_quant": false,
35
+ "llm_int8_enable_fp32_cpu_offload": false,
36
+ "llm_int8_has_fp16_weight": false,
37
+ "llm_int8_skip_modules": null,
38
+ "llm_int8_threshold": 6.0,
39
+ "load_in_4bit": true,
40
+ "load_in_8bit": false,
41
+ "quant_method": "bitsandbytes"
42
+ },
43
+ "rope_theta": 8000000.0,
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.39.0.dev0",
46
+ "use_cache": true,
47
+ "vocab_size": 256000
48
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 255001,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.39.0.dev0"
7
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf40a2ff653aad05e38a39957eb2b827f6ac967253779fdc5219bd49e11a866
3
+ size 4911554148
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d06b06de74127b4155c8e2497233841e5a0cc93e3f1287b6231172dee41db6
3
+ size 4983062520
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d55564e9cc3a460a8fcccb552f3af799da8e1158428eeb4137377964fee212c
3
+ size 4973624285
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a835be9d874af1d3de99c90655b7a2712bd31c2aebf1eb68890c8bd2acd612e
3
+ size 4945296878
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acf90b8deb618f181d47a7cfd48f2b5d0151ccad45fb236ed5ab7973997dfe27
3
+ size 2878500265
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff