Hugging Face's logo

mlabonne
/
TwinLlama-3.1-8B

Text Generation
Transformers
Safetensors
English
llama
unsloth
trl
sft
text-generation-inference
Inference Endpoints
Model card Files Community
3
mlabonne commited on
Commit
9ca0d38
•
1 Parent(s): 95a137f

Trained with Unsloth

Browse files
Files changed (7) hide show
  1. README.md +6 -6
  2. config.json +7 -3
  3. generation_config.json +5 -2
  4. model-00001-of-00004.safetensors +1 -1
  5. model-00002-of-00004.safetensors +1 -1
  6. model-00003-of-00004.safetensors +1 -1
  7. model-00004-of-00004.safetensors +1 -1
README.md CHANGED
@@ -1,15 +1,15 @@
1
  ---
 
 
 
 
 
2
  library_name: transformers
 
3
  tags:
4
  - unsloth
5
  - trl
6
  - sft
7
- license: apache-2.0
8
- datasets:
9
- - mlabonne/llmtwin
10
- language:
11
- - en
12
- base_model: meta-llama/Meta-Llama-3.1-8B
13
  ---
14
 
15
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/Ddo6O27iJ0uFiGp7Y5py1.png)
 
1
  ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B
3
+ datasets:
4
+ - mlabonne/llmtwin
5
+ language:
6
+ - en
7
  library_name: transformers
8
+ license: apache-2.0
9
  tags:
10
  - unsloth
11
  - trl
12
  - sft
 
 
 
 
 
 
13
  ---
14
 
15
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/Ddo6O27iJ0uFiGp7Y5py1.png)
config.json CHANGED
@@ -1,12 +1,16 @@
1
  {
2
- "_name_or_path": "unsloth/Meta-Llama-3.1-8B",
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,
@@ -31,7 +35,7 @@
31
  "tie_word_embeddings": false,
32
  "torch_dtype": "bfloat16",
33
  "transformers_version": "4.44.2",
34
- "unsloth_version": "2024.8",
35
  "use_cache": true,
36
  "vocab_size": 128256
37
  }
 
1
  {
2
+ "_name_or_path": "mlabonne/Llama-3.1-8B",
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,
 
35
  "tie_word_embeddings": false,
36
  "torch_dtype": "bfloat16",
37
  "transformers_version": "4.44.2",
38
+ "unsloth_version": "2024.9.post4",
39
  "use_cache": true,
40
  "vocab_size": 128256
41
  }
generation_config.json CHANGED
@@ -1,8 +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,
 
1
  {
 
2
  "bos_token_id": 128000,
3
  "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
  "max_length": 131072,
10
  "pad_token_id": 128004,
11
  "temperature": 0.6,
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75392c61e91fdbd94f2d8fb2403f22282957d81160939a10c28870732f6fa3ab
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67271b802b4279f0bef010ea71b6934f636cec71cf1519e40ce7a304b04719a5
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:d8b17337fb10c5b153636b4c5e0e56fce927df3b31feea11f75af18ee96e993f
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bf4aa11a4c6d8cfa58384a7301494789e1334cd9be0f000be07e94f32b9928
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ec7d5edebb2c5e3d4589ed9caf54696e544150597f4f50f70a39d3a0c4bb89e
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e3c88e517da80b03decfd01a8750593fb14bdcc5a15e7ffbbbfe2e795c399c6
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:e031ee5e5bc29128ad6489bc237b3440c81b0316972f92bf87cc85eec34b2b5a
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8629c656223b718a9ff445ca07f26f716746321918a18ceae4514c8d446b9c9
3
  size 1168138808