Hugging Face's logo

FriendliAI
/
Meta-Llama-3.1-70B-Instruct-fp8

Text Generation
Safetensors
PyTorch
English
llama
facebook
meta
llama-3
conversational
8-bit precision
fp8
Model card Files Community
seungahdev commited on
Commit
1187d33
•
1 Parent(s): 2b85b4f

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +7 -3
  2. generation_config.json +1 -1
  3. model-00001-of-00008.safetensors +1 -1
  4. model-00002-of-00008.safetensors +1 -1
  5. model-00003-of-00008.safetensors +1 -1
  6. model-00004-of-00008.safetensors +1 -1
  7. model-00005-of-00008.safetensors +1 -1
  8. model-00006-of-00008.safetensors +1 -1
  9. model-00007-of-00008.safetensors +1 -1
  10. model-00008-of-00008.safetensors +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": ".",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -11,7 +11,7 @@
11
  128008,
12
  128009
13
  ],
14
- "fmo_version": "0.2",
15
  "hidden_act": "silu",
16
  "hidden_size": 8192,
17
  "initializer_range": 0.02,
@@ -23,6 +23,10 @@
23
  "num_hidden_layers": 80,
24
  "num_key_value_heads": 8,
25
  "pretraining_tp": 1,
 
 
 
 
26
  "rms_norm_eps": 1e-05,
27
  "rope_scaling": {
28
  "factor": 8.0,
@@ -34,7 +38,7 @@
34
  "rope_theta": 500000.0,
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "bfloat16",
37
- "transformers_version": "4.43.2",
38
  "use_cache": true,
39
  "use_fp8_e4m3": true,
40
  "vocab_size": 128256
 
1
  {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
11
  128008,
12
  128009
13
  ],
14
+ "fmo_version": "0.4",
15
  "hidden_act": "silu",
16
  "hidden_size": 8192,
17
  "initializer_range": 0.02,
 
23
  "num_hidden_layers": 80,
24
  "num_key_value_heads": 8,
25
  "pretraining_tp": 1,
26
+ "quantization_config": {
27
+ "activation_scheme": "static",
28
+ "quant_method": "fp8"
29
+ },
30
  "rms_norm_eps": 1e-05,
31
  "rope_scaling": {
32
  "factor": 8.0,
 
38
  "rope_theta": 500000.0,
39
  "tie_word_embeddings": false,
40
  "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.44.2",
42
  "use_cache": true,
43
  "use_fp8_e4m3": true,
44
  "vocab_size": 128256
generation_config.json CHANGED
@@ -8,5 +8,5 @@
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
- "transformers_version": "4.43.2"
12
  }
 
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
  }
model-00001-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7344700f2e1c4502d148dcd16f64c197e1cb5b194b8ae8442838988fb371928a
3
  size 9953401440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65fdee671a412ce9e276f32e1dae692ff385c14b5961530b9cf23cdfd52eec62
3
  size 9953401440
model-00002-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe46c366f59ed48de160c91187e812b1c55c29a61e909dedd826398d3db222d6
3
  size 9882167936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b116171bd4747769ef09304d8caa5458ee3c03e7616b9bf94d8f36802463ff9
3
  size 9882167936
model-00003-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9530360a73404d43a72bba2384bfa0bdf17b4e96d42d752455f3b44bb3efa9b8
3
  size 9798315824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c67e0224caa28437dcf2e14ceef5c522977d6ad98933cee3f99d8f77c63bd070
3
  size 9798315824
model-00004-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a65b87e0b4b76a0318025d755a9b7f5bdaeafaf3507d34fc9cda4576a33971d
3
  size 9882167952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cd71648d4590551580bf6867435a137a6eaa39335578f4be737dc273665fc9e
3
  size 9882167952
model-00005-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c802c81746718be07c9670a065d678f1c96a086379ecf1feb958a4418c096af8
3
  size 9798315824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2b8fce24d5c8fe2683dce504417c1a1ef453133e32e33e99bed91cf34ec065
3
  size 9798315824
model-00006-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82a879e871821e0d77d9675f13927f63e5c2888011e94be5cd2669bf2b317e3c
3
  size 9882167952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a0392cbaeb6f7c4b5783ba63a52d729032628ca854a5e03f3fcd4a86761cb16
3
  size 9882167952
model-00007-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b75236ac24c78a647bf82611e70861b577cf022ccf3af1273086d7d8bc9d092
3
  size 9798315824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85113a44c7973dd42e2c37493d05c143f45db332d7480545068f378b9d859e66
3
  size 9798315824
model-00008-of-00008.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b601f83f86f04030a1a7f9f31c44d1e6d21bceb5bfd670b632318ce7d3ca06c
3
  size 3661713432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:980e308bf5d684159d6786b573bbbdbff8863443c84bec4b2114656021318a07
3
  size 3661713432