fsaudm commited on
Commit
6f2e91d
1 Parent(s): 192f79a

Upload LlamaForCausalLM

Browse files
README.md CHANGED
@@ -1,10 +1,5 @@
1
  ---
2
- library_name: transformers
3
  base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
4
- license: llama3.1
5
- model-index:
6
- - name: Meta-Llama-3.1-70B-Instruct-INT4
7
- results: []
8
  language:
9
  - en
10
  - de
@@ -14,12 +9,17 @@ language:
14
  - hi
15
  - es
16
  - th
 
 
17
  tags:
18
  - facebook
19
  - meta
20
  - pytorch
21
  - llama
22
  - llama-3
 
 
 
23
  ---
24
 
25
  # Model Card for Model ID
 
1
  ---
 
2
  base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
 
 
 
 
3
  language:
4
  - en
5
  - de
 
9
  - hi
10
  - es
11
  - th
12
+ library_name: transformers
13
+ license: llama3.1
14
  tags:
15
  - facebook
16
  - meta
17
  - pytorch
18
  - llama
19
  - llama-3
20
+ model-index:
21
+ - name: Meta-Llama-3.1-70B-Instruct-INT4
22
+ results: []
23
  ---
24
 
25
  # Model Card for Model ID
config.json CHANGED
@@ -25,11 +25,11 @@
25
  "quantization_config": {
26
  "_load_in_4bit": true,
27
  "_load_in_8bit": false,
28
- "bnb_4bit_compute_dtype": "float32",
29
  "bnb_4bit_quant_storage": "uint8",
30
- "bnb_4bit_quant_type": "fp4",
31
- "bnb_4bit_use_double_quant": false,
32
- "llm_int8_enable_fp32_cpu_offload": false,
33
  "llm_int8_has_fp16_weight": false,
34
  "llm_int8_skip_modules": null,
35
  "llm_int8_threshold": 6.0,
@@ -47,7 +47,7 @@
47
  },
48
  "rope_theta": 500000.0,
49
  "tie_word_embeddings": false,
50
- "torch_dtype": "float16",
51
  "transformers_version": "4.43.2",
52
  "use_cache": true,
53
  "vocab_size": 128256
 
25
  "quantization_config": {
26
  "_load_in_4bit": true,
27
  "_load_in_8bit": false,
28
+ "bnb_4bit_compute_dtype": "bfloat16",
29
  "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "nf4",
31
+ "bnb_4bit_use_double_quant": true,
32
+ "llm_int8_enable_fp32_cpu_offload": true,
33
  "llm_int8_has_fp16_weight": false,
34
  "llm_int8_skip_modules": null,
35
  "llm_int8_threshold": 6.0,
 
47
  },
48
  "rope_theta": 500000.0,
49
  "tie_word_embeddings": false,
50
+ "torch_dtype": "bfloat16",
51
  "transformers_version": "4.43.2",
52
  "use_cache": true,
53
  "vocab_size": 128256
model-00001-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f04cbd8f2bc235453ea5457ccdda15d14d3d12a02de21b57111866b9a4d6f003
3
+ size 4949082290
model-00002-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd890071c67995f897924f539401984791acfbd5cb6c08f7ddd6394f43c2c7b8
3
+ size 4977054940
model-00003-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b1f5d22b413e6043b431ccd4ff142b43b6788dbbcef009da272cf4826c0f37
3
+ size 4977088094
model-00004-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab428b4f7c89d580c55e8283be380973f256d7ab92ae5ffb3280dcc8bcb48a9e
3
+ size 4933786845
model-00005-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bff8f0032f6b4ec5ca3e24d28cf30dd9f9deb86e3538a01f967218a7005bfd
3
+ size 4977055132
model-00006-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e81ccd976d2e883ca2b79157b2223cc90d4ee38189f8194372bdedce0df244
3
+ size 4977055097
model-00007-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e78a6f4902f5dea55bfc57451a80b2790e0cc4c184f77c198395f8cc66bdca6
3
+ size 4977088084
model-00008-of-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ca67d01dffc9286724570664a9bd8e0a47eaa6f3459d85844aafb6a9e80dfb
3
+ size 4750027590
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff