Hugging Face's logo

qkrqudwn2
/
Llama3-weeslee-Ko-3-8B

Text Generation
Transformers
Safetensors
llama
trl
sft
conversational
text-generation-inference
Model card Files
xet
Community
qkrqudwn2 commited on
Commit
1634baa
·
verified ·
1 Parent(s): 0bbd36b

Upload LlamaForCausalLM

Browse files
Files changed (10) hide show
  1. config.json +1 -16
  2. generation_config.json +1 -1
  3. model-00001-of-00007.safetensors +3 -0
  4. model-00002-of-00007.safetensors +3 -0
  5. model-00003-of-00007.safetensors +3 -0
  6. model-00004-of-00007.safetensors +3 -0
  7. model-00005-of-00007.safetensors +3 -0
  8. model-00006-of-00007.safetensors +3 -0
  9. model-00007-of-00007.safetensors +3 -0
  10. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -19,27 +19,12 @@
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 8,
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": null,
39
  "rope_theta": 500000.0,
40
  "tie_word_embeddings": false,
41
  "torch_dtype": "float32",
42
- "transformers_version": "4.48.2",
43
  "use_cache": false,
44
  "vocab_size": 128256
45
  }
 
19
  "num_hidden_layers": 32,
20
  "num_key_value_heads": 8,
21
  "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "rms_norm_eps": 1e-05,
23
  "rope_scaling": null,
24
  "rope_theta": 500000.0,
25
  "tie_word_embeddings": false,
26
  "torch_dtype": "float32",
27
+ "transformers_version": "4.49.0.dev0",
28
  "use_cache": false,
29
  "vocab_size": 128256
30
  }
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "max_length": 4096,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
- "transformers_version": "4.48.2"
9
  }
 
5
  "max_length": 4096,
6
  "temperature": 0.6,
7
  "top_p": 0.9,
8
+ "transformers_version": "4.49.0.dev0"
9
  }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc27fbb8203dd3c1e0a1096e7206f24149ccd5f24bb58afd5bc786829f2fcc25
3
+ size 4900099808
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa15b14d04ba0563e7725b2926ae705a4e8c7c8e47725dc7e10b6c39c4c4c75
3
+ size 4849049504
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27e4b191714f662c0c55bd4cd8722420be052b65f60e59e316b955433403ec6
3
+ size 4785382440
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed3c7c404cf59330ee5c006b771d7e3fe3f14c618f516729cc32cddbbc030e8
3
+ size 4849049568
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46d20955d9240707e71e571ee895102bded16743563682bac997466e0a319dc
3
+ size 4785382472
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d46ea2d28c586c836a57827fdca739b751254e617d811394e739718280b312a4
3
+ size 4849049568
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce04195f3ad88a90556b6825cd003c2145417e21deb18d53f1dc6d027e67d670
3
+ size 3212134504
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff