Hugging Face's logo

caisarl76
/
llama2-70B-8bit

Text Generation
Transformers
PyTorch
llama
text-generation-inference
8-bit precision
Model card Files
xet
Community
caisarl76 commited on
Commit
fadca8e
·
1 Parent(s): 49b9fc3

Upload LlamaForCausalLM

Browse files
Files changed (11) hide show
  1. config.json +37 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00008.bin +3 -0
  4. pytorch_model-00002-of-00008.bin +3 -0
  5. pytorch_model-00003-of-00008.bin +3 -0
  6. pytorch_model-00004-of-00008.bin +3 -0
  7. pytorch_model-00005-of-00008.bin +3 -0
  8. pytorch_model-00006-of-00008.bin +3 -0
  9. pytorch_model-00007-of-00008.bin +3 -0
  10. pytorch_model-00008-of-00008.bin +3 -0
  11. pytorch_model.bin.index.json +0 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/llama/70B/hf/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 28672,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 64,
15
+ "num_hidden_layers": 80,
16
+ "num_key_value_heads": 8,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "quantization_config": {
20
+ "bnb_4bit_compute_dtype": "float32",
21
+ "bnb_4bit_quant_type": "fp4",
22
+ "bnb_4bit_use_double_quant": false,
23
+ "llm_int8_enable_fp32_cpu_offload": false,
24
+ "llm_int8_has_fp16_weight": false,
25
+ "llm_int8_skip_modules": null,
26
+ "llm_int8_threshold": 6.0,
27
+ "load_in_4bit": false,
28
+ "load_in_8bit": true
29
+ },
30
+ "rms_norm_eps": 1e-05,
31
+ "rope_scaling": null,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "float16",
34
+ "transformers_version": "4.31.0",
35
+ "use_cache": true,
36
+ "vocab_size": 32000
37
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
+ }
pytorch_model-00001-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7133b2f9a9859361a1f787bbaa9c64d6a7e83b90a62e9262277ffd4d4343bea3
3
+ size 9940429183
pytorch_model-00002-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a5b157e5aafd7925f6b68efe6619cc4576b8d271906c723f4fd47a09d09e10
3
+ size 9802209345
pytorch_model-00003-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac014b47bcc439a3914bb0ff309485f550234301d9c7d5549d238c19a32dcb0f
3
+ size 9970014616
pytorch_model-00004-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672f5db7da315424cab82b033c4287198aa8862ba9f9b681b62d85dd656cda58
3
+ size 9953276573
pytorch_model-00005-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb235f1653e2e8d08b2894ee9c492019bc56d8444a871d45f02b9b8cde457cd2
3
+ size 9802161039
pytorch_model-00006-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a758642a5ce3b10eaf534da3602a3a447b77bf19b592679d45acaef4f9b4ccd0
3
+ size 9886133756
pytorch_model-00007-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55428f3ad756073bd4ca1fa74afff5b15e632b5f259a7f4b58aa4c061257817
3
+ size 9651105687
pytorch_model-00008-of-00008.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f85e1a385927fa9efaf9ed234c088f5d1706c49383efc52d47941b59c47f81
3
+ size 524288938
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff