DJPanda02 commited on
Commit
c748ce0
1 Parent(s): 709cdf2

Trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -17,18 +17,6 @@
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
19
  "pretraining_tp": 1,
20
- "quantization_config": {
21
- "bnb_4bit_compute_dtype": "float16",
22
- "bnb_4bit_quant_type": "nf4",
23
- "bnb_4bit_use_double_quant": true,
24
- "llm_int8_enable_fp32_cpu_offload": false,
25
- "llm_int8_has_fp16_weight": false,
26
- "llm_int8_skip_modules": null,
27
- "llm_int8_threshold": 6.0,
28
- "load_in_4bit": true,
29
- "load_in_8bit": false,
30
- "quant_method": "bitsandbytes"
31
- },
32
  "rms_norm_eps": 1e-05,
33
  "rope_scaling": null,
34
  "rope_theta": 500000.0,
 
1
  {
2
+ "_name_or_path": "unsloth/llama-3-8b",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
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,
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5db689b8b7c4e909db091bdbb7ff0d6e4f3a2b6d4bc594c0eff34493014efea
3
+ size 4976698592
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5737bb752d56d9e94f66566815b24fc84d006b19500e064d8452ee13f9340e3a
3
+ size 4999802616
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a76df6d31fcd96a65f42dce5df0dcf92afed88b4450b6f7298611d1578208c2
3
+ size 4915916080
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e343bde652150cd0b8ac59f7e451863d9bf5d492d87fddb74df9c3ca2698e3
3
+ size 1168138808
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff