Upload LlamaForCausalLM
Browse files- config.json +13 -1
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -17,11 +17,23 @@
|
|
| 17 |
"num_hidden_layers": 22,
|
| 18 |
"num_key_value_heads": 4,
|
| 19 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 10000.0,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
-
"torch_dtype": "
|
| 25 |
"transformers_version": "4.37.1",
|
| 26 |
"use_cache": false,
|
| 27 |
"vocab_size": 32003
|
|
|
|
| 17 |
"num_hidden_layers": 22,
|
| 18 |
"num_key_value_heads": 4,
|
| 19 |
"pretraining_tp": 1,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 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": 10000.0,
|
| 35 |
"tie_word_embeddings": false,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
"transformers_version": "4.37.1",
|
| 38 |
"use_cache": false,
|
| 39 |
"vocab_size": 32003
|
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 sha256:79aa7b73c84c910ee3cc651436b42d43aa54b078fc51034030a9d66ef6e60e43
|
| 3 |
+
size 1042870362
|