Upload Phi3ForCausalLM
Browse files- config.json +16 -1
- model.safetensors +3 -0
config.json
CHANGED
@@ -22,13 +22,28 @@
|
|
22 |
"num_key_value_heads": 32,
|
23 |
"original_max_position_embeddings": 4096,
|
24 |
"pad_token_id": 32012,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"resid_pdrop": 0.0,
|
26 |
"rms_norm_eps": 1e-05,
|
27 |
"rope_scaling": null,
|
28 |
"rope_theta": 10000.0,
|
29 |
"sliding_window": 2047,
|
30 |
"tie_word_embeddings": false,
|
31 |
-
"torch_dtype": "
|
32 |
"transformers_version": "4.41.2",
|
33 |
"use_cache": true,
|
34 |
"vocab_size": 32013
|
|
|
22 |
"num_key_value_heads": 32,
|
23 |
"original_max_position_embeddings": 4096,
|
24 |
"pad_token_id": 32012,
|
25 |
+
"quantization_config": {
|
26 |
+
"_load_in_4bit": true,
|
27 |
+
"_load_in_8bit": false,
|
28 |
+
"bnb_4bit_compute_dtype": "bfloat16",
|
29 |
+
"bnb_4bit_quant_storage": "uint8",
|
30 |
+
"bnb_4bit_quant_type": "nf4",
|
31 |
+
"bnb_4bit_use_double_quant": true,
|
32 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
33 |
+
"llm_int8_has_fp16_weight": false,
|
34 |
+
"llm_int8_skip_modules": null,
|
35 |
+
"llm_int8_threshold": 6.0,
|
36 |
+
"load_in_4bit": true,
|
37 |
+
"load_in_8bit": false,
|
38 |
+
"quant_method": "bitsandbytes"
|
39 |
+
},
|
40 |
"resid_pdrop": 0.0,
|
41 |
"rms_norm_eps": 1e-05,
|
42 |
"rope_scaling": null,
|
43 |
"rope_theta": 10000.0,
|
44 |
"sliding_window": 2047,
|
45 |
"tie_word_embeddings": false,
|
46 |
+
"torch_dtype": "float32",
|
47 |
"transformers_version": "4.41.2",
|
48 |
"use_cache": true,
|
49 |
"vocab_size": 32013
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad22fc0fb2faaae9ae6dd476af0b158c2967dae0261c1bb04bda7216e4900bf9
|
3 |
+
size 2657260888
|