Hugging Face's logo

RaphaelMourad
/
Mistral-Codon-v1-117M

Text Generation
Transformers
Safetensors
mixtral
pretrained
mistral
DNA
codon
text-generation-inference
Inference Endpoints
Model card Files Community
RaphaelMourad commited on
Commit
fe9696d
·
verified ·
1 Parent(s): 0e234cb

Upload 10 files

Browse files
Files changed (7) hide show
  1. config.json +3 -2
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. rng_state.pth +1 -1
  5. scheduler.pt +1 -1
  6. trainer_state.json +0 -0
  7. training_args.bin +2 -2
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "data/models/Mixtral-8x7B-v0.2-dna",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
 
9
  "hidden_act": "silu",
10
  "hidden_size": 768,
11
  "initializer_range": 0.02,
@@ -25,7 +26,7 @@
25
  "sliding_window": null,
26
  "tie_word_embeddings": false,
27
  "torch_dtype": "bfloat16",
28
- "transformers_version": "4.42.3",
29
  "use_cache": true,
30
  "vocab_size": 69
31
  }
 
1
  {
2
+ "_name_or_path": "../MistralModels/models/Mixtral-8x7B-v0.1-small-4096",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
+ "head_dim": 96,
10
  "hidden_act": "silu",
11
  "hidden_size": 768,
12
  "initializer_range": 0.02,
 
26
  "sliding_window": null,
27
  "tie_word_embeddings": false,
28
  "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.47.1",
30
  "use_cache": true,
31
  "vocab_size": 69
32
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.42.3"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.47.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb71712478ca13d905b781ccc20f01cd790ecfe6009e0988185e6f260721751
3
  size 264608168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fd203d6dfdcff75efcd1b898fb91e76bef7217bba3db51bc309dc2fa754c95
3
  size 264608168
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3976e39bd4bbac0908cb211384118099c4e48af715c726ef4b6d1cbf191bbcd3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f05ac0ee4152d2ad0a990817be38e40d0d8babd6f9f143f96a276a18f205dae5
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab05a4708e4ff22127c526406c3ddcaf2a88a18fede6043f2ade0d78b3ee2566
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90ff8d8cd03529189eb32c4f6c5f2bc04a8371e61377b81c95def4bd83cc23b
3
  size 1064
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:771e7eeddb561c5ba5034da3dd73c3c247ab16ddfd64951f3e7cefd51e87e865
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99e9e1da9ba4ba96f3f457ae42632264224edfd8070f94541a7c17773ea3107
3
+ size 5304