Developer Zoyel commited on
Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- config.json +12 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
config.json
CHANGED
|
@@ -19,6 +19,18 @@
|
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"pad_token_id": 128004,
|
| 21 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
"rope_scaling": {
|
| 24 |
"factor": 8.0,
|
|
|
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"pad_token_id": 128004,
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
+
"quantization_config": {
|
| 23 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 24 |
+
"bnb_4bit_quant_type": "nf4",
|
| 25 |
+
"bnb_4bit_use_double_quant": true,
|
| 26 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 27 |
+
"llm_int8_has_fp16_weight": false,
|
| 28 |
+
"llm_int8_skip_modules": null,
|
| 29 |
+
"llm_int8_threshold": 6.0,
|
| 30 |
+
"load_in_4bit": true,
|
| 31 |
+
"load_in_8bit": false,
|
| 32 |
+
"quant_method": "bitsandbytes"
|
| 33 |
+
},
|
| 34 |
"rms_norm_eps": 1e-05,
|
| 35 |
"rope_scaling": {
|
| 36 |
"factor": 8.0,
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc42b9c86089e414ce8038457e88709948437a9e74bf307ef68496a6d6654adf
|
| 3 |
+
size 4652072833
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b9f8fb3a26772f655e8508705dc914ca71e511cdb96ac35b11daa6958e64dc1
|
| 3 |
+
size 1050673280
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|