Upload LlamaForCausalLM
Browse files- config.json +0 -15
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -21,21 +21,6 @@
|
|
| 21 |
"num_key_value_heads": 5,
|
| 22 |
"pad_token_id": 2,
|
| 23 |
"pretraining_tp": 1,
|
| 24 |
-
"quantization_config": {
|
| 25 |
-
"_load_in_4bit": true,
|
| 26 |
-
"_load_in_8bit": false,
|
| 27 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 28 |
-
"bnb_4bit_quant_storage": "uint8",
|
| 29 |
-
"bnb_4bit_quant_type": "nf4",
|
| 30 |
-
"bnb_4bit_use_double_quant": true,
|
| 31 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 32 |
-
"llm_int8_has_fp16_weight": false,
|
| 33 |
-
"llm_int8_skip_modules": null,
|
| 34 |
-
"llm_int8_threshold": 6.0,
|
| 35 |
-
"load_in_4bit": true,
|
| 36 |
-
"load_in_8bit": false,
|
| 37 |
-
"quant_method": "bitsandbytes"
|
| 38 |
-
},
|
| 39 |
"rms_norm_eps": 1e-05,
|
| 40 |
"rope_interleaved": false,
|
| 41 |
"rope_scaling": null,
|
|
|
|
| 21 |
"num_key_value_heads": 5,
|
| 22 |
"pad_token_id": 2,
|
| 23 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"rms_norm_eps": 1e-05,
|
| 25 |
"rope_interleaved": false,
|
| 26 |
"rope_scaling": null,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbe93adad98feca686d06adc0d70c42a99ab8eba83a84ce781ee8f5ed52527d0
|
| 3 |
+
size 1352820488
|