Hugging Face's logo

NanQiangHF
/
llama3_8b_instruct_BWRM

Text Classification
Transformers
Safetensors
llama
Generated from Trainer
trl
reward-trainer
text-generation-inference
Inference Endpoints
Model card Files Community
NanQiangHF commited on
Commit
9dbd96f
•
1 Parent(s): 09eed2f

Upload LlamaForSequenceClassification

Browse files
Files changed (5) hide show
  1. config.json +4 -14
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
config.json CHANGED
@@ -1,16 +1,12 @@
1
  {
2
- "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
3
  "architectures": [
4
  "LlamaForSequenceClassification"
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
  "id2label": {
@@ -21,7 +17,7 @@
21
  "label2id": {
22
  "LABEL_0": 0
23
  },
24
- "max_position_embeddings": 131072,
25
  "mlp_bias": false,
26
  "model_type": "llama",
27
  "num_attention_heads": 32,
@@ -29,13 +25,7 @@
29
  "num_key_value_heads": 8,
30
  "pretraining_tp": 1,
31
  "rms_norm_eps": 1e-05,
32
- "rope_scaling": {
33
- "factor": 8.0,
34
- "high_freq_factor": 4.0,
35
- "low_freq_factor": 1.0,
36
- "original_max_position_embeddings": 8192,
37
- "rope_type": "llama3"
38
- },
39
  "rope_theta": 500000.0,
40
  "tie_word_embeddings": false,
41
  "torch_dtype": "bfloat16",
 
1
  {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
  "architectures": [
4
  "LlamaForSequenceClassification"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
 
 
 
 
10
  "hidden_act": "silu",
11
  "hidden_size": 4096,
12
  "id2label": {
 
17
  "label2id": {
18
  "LABEL_0": 0
19
  },
20
+ "max_position_embeddings": 8192,
21
  "mlp_bias": false,
22
  "model_type": "llama",
23
  "num_attention_heads": 32,
 
25
  "num_key_value_heads": 8,
26
  "pretraining_tp": 1,
27
  "rms_norm_eps": 1e-05,
28
+ "rope_scaling": null,
 
 
 
 
 
 
29
  "rope_theta": 500000.0,
30
  "tie_word_embeddings": false,
31
  "torch_dtype": "bfloat16",
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0394b013e3c89438155ccc72ddfaeb958386830677673f7e87425456764046e
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f5c1be1142cdaaa1e05450f6070b8f70b0a60787265bb00b3fc29ef9d89619
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5cbf30c182809f235fe2c2a8d56e679ed00aebd167a8d1c610b77b6136b7547
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fae859b2d84fa8e20c15fe901de0295c8db227e9303b0024490ddb9c8c6574
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b55fddeb081b8f04aa3b92cdfafe4c5f58a851b653626a4663f1a59ac37d6f1
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01fbccbeb9422e0731309fd7d041fa888a1dd8eabc9af4ee59803968e140f57e
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:621d578ae97d0ca68d9165a8273b457706cc3ed549ed8c4cf37b99fb2865fa50
3
  size 117473824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5ac0e50fd76a64dc659c8f9853ec04fe6832f3ac835927ec0f593c30907eca
3
  size 117473824