Upload LlamaForCausalLM
Browse files- config.json +5 -2
- model-00001-of-00002.safetensors +2 -2
- model.safetensors.index.json +1 -1
config.json
CHANGED
|
@@ -20,7 +20,10 @@
|
|
| 20 |
"pad_token_id": 128004,
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"quantization_config": {
|
| 23 |
-
"
|
|
|
|
|
|
|
|
|
|
| 24 |
"bnb_4bit_quant_type": "nf4",
|
| 25 |
"bnb_4bit_use_double_quant": true,
|
| 26 |
"llm_int8_enable_fp32_cpu_offload": false,
|
|
@@ -43,7 +46,7 @@
|
|
| 43 |
"tie_word_embeddings": false,
|
| 44 |
"torch_dtype": "float16",
|
| 45 |
"transformers_version": "4.44.2",
|
| 46 |
-
"unsloth_version": "2024.
|
| 47 |
"use_cache": true,
|
| 48 |
"vocab_size": 128256
|
| 49 |
}
|
|
|
|
| 20 |
"pad_token_id": 128004,
|
| 21 |
"pretraining_tp": 1,
|
| 22 |
"quantization_config": {
|
| 23 |
+
"_load_in_4bit": true,
|
| 24 |
+
"_load_in_8bit": false,
|
| 25 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
| 26 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 27 |
"bnb_4bit_quant_type": "nf4",
|
| 28 |
"bnb_4bit_use_double_quant": true,
|
| 29 |
"llm_int8_enable_fp32_cpu_offload": false,
|
|
|
|
| 46 |
"tie_word_embeddings": false,
|
| 47 |
"torch_dtype": "float16",
|
| 48 |
"transformers_version": "4.44.2",
|
| 49 |
+
"unsloth_version": "2024.9",
|
| 50 |
"use_cache": true,
|
| 51 |
"vocab_size": 128256
|
| 52 |
}
|
model-00001-of-00002.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 sha256:16714047e3ffe09f943782582bf8d9bd100386a0ca37e24abdd987dc4a3506c4
|
| 3 |
+
size 4652072851
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 5702577731
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|