shri171981 commited on
Commit
e88192c
·
verified ·
1 Parent(s): 44c2933

Upload LlamaForCausalLM

Browse files
README.md CHANGED
@@ -3,13 +3,13 @@ library_name: peft
3
  base_model: unsloth/llama-3-8b-instruct-bnb-4bit
4
  pipeline_tag: text-generation
5
  tags:
6
- - medical
7
- - llama-3
8
- - text-generation
9
- - unsloth
10
- - lora
11
  language:
12
- - en
13
  ---
14
 
15
  # HACK_DOC (Medical Assistant)
 
3
  base_model: unsloth/llama-3-8b-instruct-bnb-4bit
4
  pipeline_tag: text-generation
5
  tags:
6
+ - medical
7
+ - llama-3
8
+ - text-generation
9
+ - unsloth
10
+ - lora
11
  language:
12
+ - en
13
  ---
14
 
15
  # HACK_DOC (Medical Assistant)
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "float16",
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": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128255,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "_load_in_4bit": true,
25
+ "_load_in_8bit": false,
26
+ "bnb_4bit_compute_dtype": "bfloat16",
27
+ "bnb_4bit_quant_storage": "uint8",
28
+ "bnb_4bit_quant_type": "nf4",
29
+ "bnb_4bit_use_double_quant": true,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": true,
35
+ "load_in_8bit": false,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "rope_theta": 500000.0,
41
+ "tie_word_embeddings": false,
42
+ "transformers_version": "4.57.3",
43
+ "unsloth_version": "2024.9",
44
+ "use_cache": true,
45
+ "vocab_size": 128256
46
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 8192,
9
+ "pad_token_id": 128255,
10
+ "temperature": 0.6,
11
+ "top_p": 0.9,
12
+ "transformers_version": "4.57.3"
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4467baa751f94f2ef976feabfe49518575dae7fc46638dc21b86c3fc7c6e2a4e
3
+ size 4652072864
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8005050c5e27c8232d9ce04f03631ce67bcc362c80fc57079bda23b498695c20
3
+ size 1050673280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff