Hugging Face's logo

lliu01
/
fortios

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
Community
lliu01 commited on
Commit
3379e62
·
verified ·
1 Parent(s): 83701b1

Upload LlamaForCausalLM

Browse files
Files changed (10) hide show
  1. config.json +7 -20
  2. generation_config.json +5 -4
  3. model-00001-of-00007.safetensors +1 -1
  4. model-00002-of-00007.safetensors +1 -1
  5. model-00003-of-00007.safetensors +1 -1
  6. model-00004-of-00007.safetensors +1 -1
  7. model-00005-of-00007.safetensors +1 -1
  8. model-00006-of-00007.safetensors +1 -1
  9. model-00007-of-00007.safetensors +1 -1
  10. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,12 +1,16 @@
1
  {
2
- "_name_or_path": "unsloth/Meta-Llama-3.1-8B-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
- "eos_token_id": 128001,
 
 
 
 
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
@@ -17,23 +21,7 @@
17
  "num_attention_heads": 32,
18
  "num_hidden_layers": 32,
19
  "num_key_value_heads": 8,
20
- "pad_token_id": 128004,
21
  "pretraining_tp": 1,
22
- "quantization_config": {
23
- "_load_in_4bit": true,
24
- "_load_in_8bit": false,
25
- "bnb_4bit_compute_dtype": "bfloat16",
26
- "bnb_4bit_quant_storage": "uint8",
27
- "bnb_4bit_quant_type": "nf4",
28
- "bnb_4bit_use_double_quant": true,
29
- "llm_int8_enable_fp32_cpu_offload": false,
30
- "llm_int8_has_fp16_weight": false,
31
- "llm_int8_skip_modules": null,
32
- "llm_int8_threshold": 6.0,
33
- "load_in_4bit": true,
34
- "load_in_8bit": false,
35
- "quant_method": "bitsandbytes"
36
- },
37
  "rms_norm_eps": 1e-05,
38
  "rope_scaling": {
39
  "factor": 8.0,
@@ -44,9 +32,8 @@
44
  },
45
  "rope_theta": 500000.0,
46
  "tie_word_embeddings": false,
47
- "torch_dtype": "float16",
48
  "transformers_version": "4.44.0",
49
- "unsloth_version": "2024.8",
50
  "use_cache": true,
51
  "vocab_size": 128256
52
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
  "hidden_act": "silu",
15
  "hidden_size": 4096,
16
  "initializer_range": 0.02,
 
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
 
24
  "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  "rms_norm_eps": 1e-05,
26
  "rope_scaling": {
27
  "factor": 8.0,
 
32
  },
33
  "rope_theta": 500000.0,
34
  "tie_word_embeddings": false,
35
+ "torch_dtype": "float32",
36
  "transformers_version": "4.44.0",
 
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
generation_config.json CHANGED
@@ -1,10 +1,11 @@
1
  {
2
- "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
- "eos_token_id": 128001,
6
- "max_length": 131072,
7
- "pad_token_id": 128004,
 
 
8
  "temperature": 0.6,
9
  "top_p": 0.9,
10
  "transformers_version": "4.44.0"
 
1
  {
 
2
  "bos_token_id": 128000,
3
  "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
  "transformers_version": "4.44.0"
model-00001-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85de022225908eebafe3533958236e330ccc97f3735a69051bf115e98f0f71b1
3
  size 4886466168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d14cc5f2a03a721e186beb267fff867da0ed2cf8a60d498e4ee2cd618d1adfdf
3
  size 4886466168
model-00002-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:483bdfd75328c6016993acc4694ef5ca2f6029c8576d2e4f72d5018d0bcf1162
3
  size 4832007448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca31d2466b53fce44243bd1fb61db6b20607c13c65e3dcd4df388d65f379e46
3
  size 4832007448
model-00003-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0dd25ad96c0ed4fa1f7be62e89842d74b3cee101d6623883e38131b968f8a50
3
  size 4999813112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86611f1f29bc67abfe500b522864396fba696c1b9273dde9033db3c181f36c2a
3
  size 4999813112
model-00004-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2db579a08620445091b88f359e586d69811cd35f85d67a5c3c40977ae87be505
3
  size 4999813128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bc28b473b551116c26efcda66e8b9d0f185e822e3db676d8838933e0a1aee6
3
  size 4999813128
model-00005-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9133b7d4636287b879826a25c59a820a7c632fd0c232faedacf27e982cec9bcc
3
  size 4832007496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa3c0cbd972e657a25bd36f73001e71a6c340362c7f00ee408eaf542cc12692
3
  size 4832007496
model-00006-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1785d03a4be712e6d45b198cc51ddfdfeab9aacda5f4497afc975c86c3874126
3
  size 4999813120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43ce2f34685956c120bb869d344a620fb7329100e45bc862baac8864b7f656f
3
  size 4999813120
model-00007-of-00007.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aed5abe69104c5784d3d53e0afe545b478acf8729dfbffe07dabe62ce2aae16
3
  size 2571158184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cc38bf86f7fbb6d3c107ce84ebdadb4d5fc118a875767d4bdd48960f7555d73
3
  size 2571158184
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff