Hugging Face's logo

weege007
/
llama-3-8b-bnb-4bit-alpaca-merged-4bit

Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
unsloth
trl
sft
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
weege007 commited on
Commit
3803432
•
1 Parent(s): 5bf2e77

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show
  1. README.md +1 -0
  2. config.json +0 -1
  3. model-00001-of-00002.safetensors +2 -2
  4. model.safetensors.index.json +1 -1
README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - unsloth
9
  - llama
10
  - trl
 
11
  base_model: unsloth/llama-3-8b-bnb-4bit
12
  ---
13
 
 
8
  - unsloth
9
  - llama
10
  - trl
11
+ - sft
12
  base_model: unsloth/llama-3-8b-bnb-4bit
13
  ---
14
 
config.json CHANGED
@@ -16,7 +16,6 @@
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
- "pad_token_id": 128001,
20
  "pretraining_tp": 1,
21
  "quantization_config": {
22
  "bnb_4bit_compute_dtype": "float16",
 
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
 
19
  "pretraining_tp": 1,
20
  "quantization_config": {
21
  "bnb_4bit_compute_dtype": "float16",
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5181c71aa33dce58798e6fa334c76e40479696e3c7a2aef85ad6bcfc66409bce
3
- size 4652072883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6467b37bbc58d5be83a7da28791f8cf84bd7659be11305190fb04578bf7c4c1c
3
+ size 4652072868
model.safetensors.index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "metadata": {
3
- "total_size": 5702577763
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00002-of-00002.safetensors",
 
1
  {
2
  "metadata": {
3
+ "total_size": 5702577748
4
  },
5
  "weight_map": {
6
  "lm_head.weight": "model-00002-of-00002.safetensors",