DRXD1000 commited on
Commit
cb874c6
1 Parent(s): 0f6da90

Upload MistralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +51 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/proj/Phoenix/DRXD1000-Phoenix_GPTQ_4bit",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
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": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "batch_size": 1,
20
+ "bits": 4,
21
+ "block_name_to_quantize": "model.layers",
22
+ "cache_block_outputs": true,
23
+ "damp_percent": 0.1,
24
+ "dataset": "c4",
25
+ "desc_act": false,
26
+ "exllama_config": {
27
+ "version": 2
28
+ },
29
+ "group_size": 128,
30
+ "max_input_length": null,
31
+ "model_seqlen": 4096,
32
+ "module_name_preceding_first_block": [
33
+ "model.embed_tokens"
34
+ ],
35
+ "pad_token_id": null,
36
+ "quant_method": "gptq",
37
+ "sym": true,
38
+ "tokenizer": null,
39
+ "true_sequential": true,
40
+ "use_cuda_fp16": false,
41
+ "use_exllama": false
42
+ },
43
+ "rms_norm_eps": 1e-05,
44
+ "rope_theta": 10000.0,
45
+ "sliding_window": 4096,
46
+ "tie_word_embeddings": false,
47
+ "torch_dtype": "float16",
48
+ "transformers_version": "4.36.2",
49
+ "use_cache": true,
50
+ "vocab_size": 32000
51
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5ecab78475e158575b16d63a38ec9fb3444ecb37b18d5a8023ef27d881016a
3
+ size 4158662096