Commit
•
379bae4
1
Parent(s):
9eb3fff
Upload LlamaForCausalLM
Browse files- config.json +12 -1
- pytorch_model.bin +3 -0
config.json
CHANGED
|
@@ -15,9 +15,20 @@
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"pad_token_id": -1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
"rms_norm_eps": 1e-06,
|
| 19 |
"tie_word_embeddings": false,
|
| 20 |
-
"torch_dtype": "
|
| 21 |
"transformers_version": "4.30.2",
|
| 22 |
"use_cache": true,
|
| 23 |
"vocab_size": 32000
|
|
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"pad_token_id": -1,
|
| 18 |
+
"quantization_config": {
|
| 19 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 20 |
+
"bnb_4bit_quant_type": "fp4",
|
| 21 |
+
"bnb_4bit_use_double_quant": false,
|
| 22 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 23 |
+
"llm_int8_has_fp16_weight": false,
|
| 24 |
+
"llm_int8_skip_modules": null,
|
| 25 |
+
"llm_int8_threshold": 6.0,
|
| 26 |
+
"load_in_4bit": false,
|
| 27 |
+
"load_in_8bit": true
|
| 28 |
+
},
|
| 29 |
"rms_norm_eps": 1e-06,
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
+
"torch_dtype": "float16",
|
| 32 |
"transformers_version": "4.30.2",
|
| 33 |
"use_cache": true,
|
| 34 |
"vocab_size": 32000
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:066344301a1864a4d77ff9389c4413241147420c4758b4e372d4d2bdb8710f0b
|
| 3 |
+
size 7006454217
|