Hugging Face's logo

nroggendorff
/
mayo

Text Generation
Transformers
Safetensors
English
mistral
trl
sft
sgd
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
nroggendorff commited on
Commit
f26166d
·
verified ·
1 Parent(s): ffecbde

Upload MistralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +18 -31
  2. generation_config.json +2 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,22 +1,20 @@
1
  {
2
- "_name_or_path": "gpt2",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
 
11
  "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 1024,
20
  "quantization_config": {
21
  "_load_in_4bit": true,
22
  "_load_in_8bit": false,
@@ -32,23 +30,12 @@
32
  "load_in_8bit": false,
33
  "quant_method": "bitsandbytes"
34
  },
35
- "reorder_and_upcast_attn": false,
36
- "resid_pdrop": 0.1,
37
- "scale_attn_by_inverse_layer_idx": false,
38
- "scale_attn_weights": true,
39
- "summary_activation": null,
40
- "summary_first_dropout": 0.1,
41
- "summary_proj_to_labels": true,
42
- "summary_type": "cls_index",
43
- "summary_use_proj": true,
44
- "task_specific_params": {
45
- "text-generation": {
46
- "do_sample": true,
47
- "max_length": 50
48
- }
49
- },
50
  "torch_dtype": "float32",
51
  "transformers_version": "4.42.4",
52
  "use_cache": true,
53
- "vocab_size": 50257
54
  }
 
1
  {
2
+ "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
 
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
  "_load_in_4bit": true,
20
  "_load_in_8bit": false,
 
30
  "load_in_8bit": false,
31
  "quant_method": "bitsandbytes"
32
  },
33
+ "rms_norm_eps": 1e-05,
34
+ "rope_theta": 1000000.0,
35
+ "sliding_window": null,
36
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.42.4",
39
  "use_cache": true,
40
+ "vocab_size": 32768
41
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.42.4"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
  "transformers_version": "4.42.4"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e30df4e38b0fef0d1703187203cab2f4fe9ef8a9b891f2f8895515e07ddd5cc9
3
- size 201938082
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f77b78c7e4e84ddcdb4517a91062e65882a6b840427419727758a9f87c4c47e2
3
+ size 4675678979