danielhanchen commited on
Commit
2d59760
1 Parent(s): 8505bcc

Upload LlamaForCausalLM

Browse files
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "codellama/CodeLlama-34b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 22016,
14
+ "max_position_embeddings": 16384,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 2,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "bnb_4bit_compute_dtype": "bfloat16",
23
+ "bnb_4bit_quant_type": "nf4",
24
+ "bnb_4bit_use_double_quant": true,
25
+ "llm_int8_enable_fp32_cpu_offload": false,
26
+ "llm_int8_has_fp16_weight": false,
27
+ "llm_int8_skip_modules": null,
28
+ "llm_int8_threshold": 6.0,
29
+ "load_in_4bit": true,
30
+ "load_in_8bit": false,
31
+ "quant_method": "bitsandbytes"
32
+ },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_scaling": null,
35
+ "rope_theta": 1000000,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.37.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 32000
41
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.37.0.dev0"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a842ab1ff767d4349e9665b586a57134e2e6fe0d43829c1f7ffd2db526895b8
3
+ size 4979943041
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f1fffbc0e06334e80cc3a4404445c47b1add171b0e2ddc58f1c1997e184564
3
+ size 4998830767
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8f946753b975f08c7007c867f230dfc25e65c77d9980b1454c0537ddedcd92
3
+ size 4998830770
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:416477e8f934b5c702a5756f64ae78b880f57825d6b7fea1ca6aad3708291616
3
+ size 3209836095
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff