Hugging Face's logo

ricdomolm
/
lawma-8b

Text Generation
Transformers
Safetensors
English
llama
legal
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
ricdomolm commited on
Commit
cf7b908
•
1 Parent(s): 271c55c

Upload LlamaForCausalLM

Browse files
Files changed (6) hide show
  1. config.json +12 -5
  2. generation_config.json +8 -3
  3. model-00001-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00004-of-00004.safetensors +1 -1
config.json CHANGED
@@ -1,17 +1,18 @@
1
  {
2
- "_name_or_path": "/fast/rolmedo/test/v6/llama-3-8b-3e-56",
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,
13
  "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 32,
@@ -19,11 +20,17 @@
19
  "num_key_value_heads": 8,
20
  "pretraining_tp": 1,
21
  "rms_norm_eps": 1e-05,
22
- "rope_scaling": null,
 
 
 
 
 
 
23
  "rope_theta": 500000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.41.1",
27
  "use_cache": false,
28
  "vocab_size": 128256
29
  }
 
1
  {
2
+ "_name_or_path": "/fast/rolmedo/lawma-models/8b-8k-3e/",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
  "hidden_act": "silu",
12
  "hidden_size": 4096,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
  "mlp_bias": false,
17
  "model_type": "llama",
18
  "num_attention_heads": 32,
 
20
  "num_key_value_heads": 8,
21
  "pretraining_tp": 1,
22
  "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
  "rope_theta": 500000.0,
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.44.2",
34
  "use_cache": false,
35
  "vocab_size": 128256
36
  }
generation_config.json CHANGED
@@ -1,7 +1,12 @@
1
  {
2
- "_from_model_config": true,
3
  "bos_token_id": 128000,
4
  "do_sample": true,
5
- "eos_token_id": 128001,
6
- "transformers_version": "4.41.1"
 
 
 
 
 
 
7
  }
 
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": "4.44.2"
12
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40452931c1dc2ced5bba83dcbc61fd3630a16ecb12ad145df9b241e65dcb05f3
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5e33e3774c70baee7bde8836cc1a8072c74372ac645a6fea66520995882db6
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:fa153a6875ec126a987a0a438a1c45c0c224dcb816dc3603e9deeaea6e77fb47
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6751163434ed2f7f2bd9c0faddbbf6fd671e8677f943732b58c7bd57be3b0c62
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f316b5ed6fa1c63558b585cf678d89ece764c031fa5e4421f62fca15c5bbe13
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ff3e531f46217348189647771b6d13ada0a10020d8a38d9bfe405fb577ce51
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09c979d848c4b4c6d215b2d6cb34f67a9ae5de9030f1849c600dd69e66c6d2ae
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc78c937593614519ae70cb7c0b8d1bb2f21f082754da75d4ee96e26cb956200
3
  size 1168138808