Hugging Face's logo

nglain
/
mistral_large_ft_autofp8

Safetensors
mistral
fp8
Model card Files Community
2
nglain commited on
Commit
d6f109f
•
1 Parent(s): 0764a6a

717dac0467e5dc6be817cbb39f783e7ca2cc6a267065420633962ff2a0324f0b

Browse files
Files changed (8) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +34 -0
  2. config.json +34 -0
  3. generation_config.json +6 -0
  4. model.safetensors.index.json +0 -0
  5. special_tokens_map.json +23 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +0 -0
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/mistral_large_ft",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 12288,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 96,
17
+ "num_hidden_layers": 88,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "activation_scheme": "dynamic",
21
+ "ignored_layers": [
22
+ "lm_head"
23
+ ],
24
+ "quant_method": "fp8"
25
+ },
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32768
34
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/mistral_large_ft",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 12288,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 131072,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 96,
17
+ "num_hidden_layers": 88,
18
+ "num_key_value_heads": 8,
19
+ "quantization_config": {
20
+ "activation_scheme": "dynamic",
21
+ "ignored_layers": [
22
+ "lm_head"
23
+ ],
24
+ "quant_method": "fp8"
25
+ },
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.44.2",
32
+ "use_cache": true,
33
+ "vocab_size": 32768
34
+ }
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": "4.44.2"
6
+ }
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
3
+ size 587583
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff