Hugging Face's logo

mjyoo2
/
kullm_arc_ft

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
8-bit precision
bitsandbytes
Model card Files Community
mjyoo2 commited on
Commit
4045eeb
·
verified ·
1 Parent(s): e9a44b9

Upload LlamaForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +15 -0
  2. model-00001-of-00003.safetensors +1 -1
  3. model-00002-of-00003.safetensors +1 -1
  4. model-00003-of-00003.safetensors +1 -1
  5. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -18,6 +18,21 @@
18
  "num_key_value_heads": 8,
19
  "pad_token_id": 2,
20
  "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "rms_norm_eps": 1e-05,
22
  "rope_scaling": null,
23
  "rope_theta": 10000.0,
 
18
  "num_key_value_heads": 8,
19
  "pad_token_id": 2,
20
  "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": false,
23
+ "_load_in_8bit": true,
24
+ "bnb_4bit_compute_dtype": "float32",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "fp4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": false,
33
+ "load_in_8bit": true,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
  "rms_norm_eps": 1e-05,
37
  "rope_scaling": null,
38
  "rope_theta": 10000.0,
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2113d6db649fe4f2961fdc71847e8878127d2288fe96dbe09a1ad391b977b20c
3
  size 4947097024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861acc86fe783ca42f558e5357b911494645832174a876b650103b22fd267169
3
  size 4947097024
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdcd57d0c9ee84541b910ca96cbe0958b7afe0c3fa5febcd1378a8560a365348
3
  size 4962001280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6173d76eea4458e5d747596b6b96b239fd468c74ca4672c65c5e2f300ee64f70
3
  size 4962001280
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b785a97426f0a7b8b464a7e4b2dcd891db47684686944a43fe761db2aeeceb
3
  size 1093346024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82963db4a25466191372b83a63f0c7e23b0e3ed505390077a4c57f82ce8e9f06
3
  size 1093346024
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff