Upload config.json with huggingface_hub
Browse files- config.json +41 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./2x_bagel-34b-v0.2_ultra_fp32",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 200000,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 56,
|
18 |
+
"num_hidden_layers": 100,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 5000000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.41.2",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 64000,
|
30 |
+
"quantization_config": {
|
31 |
+
"quant_method": "exl2",
|
32 |
+
"version": "0.1.8",
|
33 |
+
"bits": 2.8,
|
34 |
+
"head_bits": 6,
|
35 |
+
"calibration": {
|
36 |
+
"rows": 100,
|
37 |
+
"length": 2048,
|
38 |
+
"dataset": "erotiquant2.parquet"
|
39 |
+
}
|
40 |
+
}
|
41 |
+
}
|