fsndzomga commited on
Commit
699f899
·
verified ·
1 Parent(s): 2682c7a

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. README.md +7 -4
  2. config.json +28 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- library_name: transformers
3
- tags: []
4
  ---
5
 
6
  # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
 
 
 
1
  ---
2
+ base_model: CohereForAI/aya-23-8B
3
+ library_name: peft
4
  ---
5
 
6
  # Model Card for Model ID
 
15
 
16
  <!-- Provide a longer summary of what this model is. -->
17
 
18
+
19
 
20
  - **Developed by:** [More Information Needed]
21
  - **Funded by [optional]:** [More Information Needed]
 
196
 
197
  ## Model Card Contact
198
 
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CohereForAI/aya-23-8B",
3
+ "architectures": [
4
+ "CohereForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 5,
9
+ "eos_token_id": 255001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "layer_norm_eps": 1e-05,
15
+ "logit_scale": 0.0625,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "cohere",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 0,
22
+ "rope_theta": 10000,
23
+ "torch_dtype": "float16",
24
+ "transformers_version": "4.42.4",
25
+ "use_cache": true,
26
+ "use_qk_norm": false,
27
+ "vocab_size": 256000
28
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681d6dcf0f43ca3078bc6b9b8696ef83359d37175ae4f1c5e1360f6f17ea6fea
3
+ size 32125992678
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12cfd1e48b83f8c4886e20ae55741d97af93ee5df31310622a9c258fda16b78
3
+ size 5048