thomasgauthier commited on
Commit
1bbe083
1 Parent(s): 326ecfe

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. README.md +23 -0
  2. adapter_config.json +33 -0
  3. adapter_model.safetensors +3 -0
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: []
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - peft
7
+
8
+ ---
9
+ # Untitled LoRA Model (1)
10
+
11
+ This is a LoRA extracted from a language model. It was extracted using [mergekit](https://github.com/arcee-ai/mergekit).
12
+
13
+ ## LoRA Details
14
+
15
+ This LoRA adapter was extracted from /workspace/models/teknium_OpenHermes-2.5-Mistral-7B/ and uses /workspace/models/thomasgauthier_Mistral-7B-v0.1-zeroed_out-ChatML-base/ as a base.
16
+
17
+ ### Parameters
18
+
19
+ The following command was used to extract this LoRA adapter:
20
+
21
+ ```sh
22
+ mergekit-extract-lora /workspace/models/thomasgauthier_Mistral-7B-v0.1-zeroed_out-ChatML-base/ /workspace/models/teknium_OpenHermes-2.5-Mistral-7B/ OUTPUT_PATH --rank=256 --device=cuda:0
23
+ ```
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/workspace/models/thomasgauthier_Mistral-7B-v0.1-zeroed_out-ChatML-base/",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "loftq_config": {},
12
+ "lora_alpha": 256,
13
+ "lora_dropout": 0,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 256,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "up_proj",
23
+ "down_proj",
24
+ "v_proj",
25
+ "k_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "lm_head",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afcd47ca0e6271ffdaadbe94d2289a4607e43285b3e61b2c783540d8863cdd2c
3
+ size 2721380776