ichetandhembre commited on
Commit
49fb153
1 Parent(s): aecc07e

Upload model

Browse files
Files changed (3) hide show
  1. README.md +55 -0
  2. adapter_config.json +32 -0
  3. adapter_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: mistralai/Mistral-7B-v0.1
7
+ model-index:
8
+ - name: mistral_lora_clm_with_added_tokens
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # mistral_lora_clm_with_added_tokens
16
+
17
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-05
37
+ - train_batch_size: 8
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_steps: 10
43
+ - num_epochs: 2
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - PEFT 0.8.2
52
+ - Transformers 4.35.2
53
+ - Pytorch 2.1.0+cu121
54
+ - Datasets 2.17.1
55
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "MistralForCausalLM",
5
+ "parent_library": "transformers.models.mistral.modeling_mistral"
6
+ },
7
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
8
+ "bias": "none",
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 128,
16
+ "lora_dropout": 0.0,
17
+ "megatron_config": null,
18
+ "megatron_core": "megatron.core",
19
+ "modules_to_save": null,
20
+ "peft_type": "LORA",
21
+ "r": 64,
22
+ "rank_pattern": {},
23
+ "revision": null,
24
+ "target_modules": [
25
+ "embed_tokens",
26
+ "v_proj",
27
+ "q_proj",
28
+ "lm_head"
29
+ ],
30
+ "task_type": null,
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bcc29f526332d956ba70c133ef5a31523551f7664277e27f476bc144971c263
3
+ size 1177026136