Hugging Face's logo

umarigan
/
llama-3.1-openhermes-tr

Question Answering
Transformers
Safetensors
English
Turkish
llama
text-generation
text-generation-inference
unsloth
trl
sft
Inference Endpoints
Model card Files Community
umarigan commited on
Commit
1c09316
•
1 Parent(s): ba7e8db

Trained with Unsloth

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. config.json +14 -6
  3. generation_config.json +5 -5
  4. model-00001-of-00004.safetensors +2 -2
  5. model-00002-of-00004.safetensors +2 -2
  6. model-00003-of-00004.safetensors +2 -2
  7. model-00004-of-00004.safetensors +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  language:
3
  - en
4
  - tr
@@ -10,7 +11,6 @@ tags:
10
  - llama
11
  - trl
12
  - sft
13
- base_model: unsloth/llama-3-8b-bnb-4bit
14
  ---
15
 
16
  # Uploaded model
 
1
  ---
2
+ base_model: unsloth/llama-3-8b-bnb-4bit
3
  language:
4
  - en
5
  - tr
 
11
  - llama
12
  - trl
13
  - sft
 
14
  ---
15
 
16
  # Uploaded model
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -11,19 +11,27 @@
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
- "max_position_embeddings": 8192,
 
15
  "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
 
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
 
 
 
 
 
 
22
  "rope_theta": 500000.0,
23
  "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
- "transformers_version": "4.40.1",
26
- "unsloth_version": "2024.4",
27
  "use_cache": true,
28
  "vocab_size": 128256
29
  }
 
1
  {
2
+ "_name_or_path": "unsloth/meta-llama-3.1-8b-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
11
  "hidden_size": 4096,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
  "model_type": "llama",
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
  "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": "4.43.1",
34
+ "unsloth_version": "2024.7",
35
  "use_cache": true,
36
  "vocab_size": 128256
37
  }
generation_config.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
- "eos_token_id": [
5
- 128001,
6
- 128009
7
- ],
8
- "transformers_version": "4.40.1"
9
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.43.1"
9
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b5f8700a1090276b6244727cae5b45231dc1b9d39d4fd9effb032c6b9b7b613
3
- size 4976698592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:140e6fc450bb28a9051df4d1ee9850408c6ed9fd393dc90b8d86c8e45dbb7462
3
+ size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6aff642878d8f88b806df8e6bc4d96dba7631189febb730682a7223e9e8e59ab
3
- size 4999802616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743cbc9fd5a16fc915e339dc10304f3dce0cbd40f6b2651aff3d175fd0745f62
3
+ size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e127e01a092c7dbcbfd08f7749e44b996ed458cb6019a9572f67024f74d324f
3
- size 4915916080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0438b017092bd46ce86c446622e001ccf01cecc3c42a2011735151fdf179998
3
+ size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:893da9f0cd1adb82985b129ff0a0b3be3c361ec35baafdd8dfcae723284f44b7
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8f3ed9299b3084365c043b28d115618c7283222bda309fb6b02beb31581348
3
  size 1168138808