Upload LlamaForCausalLM
Browse files- config.json +1 -1
- model.safetensors +1 -1
config.json
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
"bnb_4bit_compute_dtype": "float16",
|
23 |
-
"bnb_4bit_quant_type": "
|
24 |
"bnb_4bit_use_double_quant": false,
|
25 |
"llm_int8_enable_fp32_cpu_offload": false,
|
26 |
"llm_int8_has_fp16_weight": false,
|
|
|
20 |
"pretraining_tp": 1,
|
21 |
"quantization_config": {
|
22 |
"bnb_4bit_compute_dtype": "float16",
|
23 |
+
"bnb_4bit_quant_type": "fp4",
|
24 |
"bnb_4bit_use_double_quant": false,
|
25 |
"llm_int8_enable_fp32_cpu_offload": false,
|
26 |
"llm_int8_has_fp16_weight": false,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4826780904
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e79a44c153c663f90e0ef4a508f796452a7a4a3d8f4c7b57cf341a25cc2f7510
|
3 |
size 4826780904
|