Delete config.json
Browse files- config.json +0 -40
config.json
DELETED
@@ -1,40 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "stabilityai/StableBeluga-7B",
|
3 |
-
"architectures": [
|
4 |
-
"LlamaForCausalLM"
|
5 |
-
],
|
6 |
-
"attention_bias": false,
|
7 |
-
"bos_token_id": 1,
|
8 |
-
"eos_token_id": 2,
|
9 |
-
"hidden_act": "silu",
|
10 |
-
"hidden_size": 4096,
|
11 |
-
"initializer_range": 0.02,
|
12 |
-
"intermediate_size": 11008,
|
13 |
-
"max_position_embeddings": 4096,
|
14 |
-
"model_type": "llama",
|
15 |
-
"num_attention_heads": 32,
|
16 |
-
"num_hidden_layers": 32,
|
17 |
-
"num_key_value_heads": 32,
|
18 |
-
"pad_token_id": 0,
|
19 |
-
"pretraining_tp": 1,
|
20 |
-
"quantization_config": {
|
21 |
-
"bnb_4bit_compute_dtype": "float32",
|
22 |
-
"bnb_4bit_quant_type": "fp4",
|
23 |
-
"bnb_4bit_use_double_quant": false,
|
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": false,
|
29 |
-
"load_in_8bit": true,
|
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": "4.35.0",
|
38 |
-
"use_cache": false,
|
39 |
-
"vocab_size": 32000
|
40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|