TheBloke commited on
Commit
69dcebf
1 Parent(s): f989132

GPTQ model commit

Browse files
Files changed (3) hide show
  1. config.json +43 -0
  2. model.safetensors +3 -0
  3. quantize_config.json +10 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/ehartford_dolphin-2.5-mixtral-8x7b/source",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 1000000.0,
25
+ "router_aux_loss_coef": 0.02,
26
+ "sliding_window": 4096,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.37.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32002,
32
+ "quantization_config": {
33
+ "bits": 4,
34
+ "group_size": -1,
35
+ "damp_percent": 0.1,
36
+ "desc_act": true,
37
+ "sym": true,
38
+ "true_sequential": true,
39
+ "model_name_or_path": null,
40
+ "model_file_base_name": "model",
41
+ "quant_method": "gptq"
42
+ }
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b2c5988a1580ff72b7a84a6ee22b3882e895f46fdde621590e35fecc307b7b
3
+ size 23811582112
quantize_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": -1,
4
+ "damp_percent": 0.1,
5
+ "desc_act": true,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_name_or_path": null,
9
+ "model_file_base_name": "model"
10
+ }