Hugging Face's logo

RaphaelMourad
/
Mistral-Codon-v1-16M

Text Generation
Transformers
Safetensors
mixtral
pretrained
mistral
DNA
codon
text-generation-inference
Inference Endpoints
Model card Files Community
RaphaelMourad commited on
Commit
a344632
·
verified ·
1 Parent(s): 74b518f

Upload 10 files

Browse files
Files changed (7) hide show
  1. config.json +4 -3
  2. generation_config.json +1 -1
  3. model.safetensors +2 -2
  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-v0.1-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": 256,
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": 4096
31
  }
 
1
  {
2
+ "_name_or_path": "../MistralModels/models/Mixtral-8x7B-v0.1-tiny-4096",
3
  "architectures": [
4
  "MixtralForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
+ "head_dim": 32,
10
  "hidden_act": "silu",
11
  "hidden_size": 256,
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 sha256:305dede2fdee20d047e123615cfb249528821a5e5bc8fb00d6ab6df140526b1d
3
- size 33626152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07c1929d6874726edef5ce34aff4bdc9ed34723f70a5b48b934be0a84765e7a
3
+ size 29502416
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee92eb46fa92334cd0695596a0005ba047370328e120afcbe0600b3db0d3cf32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45da3e72605d0c7d4eabbd6ba1fadd5e43884662b4b32746d140140975e5d8cd
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7378136e562900ec12820c4ab10f2ec29f1c77d7f9389389f0212dc950cd09a2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e365f297968d011699c8485e48be3af64b799e25c17e85d2ae0ff543b7c119
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 sha256:994a3cbb8e4c8cbd2d0a1c5129132fe1751fd6126e7e06527db71e8d30027b9a
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b0ec9291e6858aec31b328148dd928b1c4b1843304c5df9f158a790aeda585
3
+ size 5304