chargoddard commited on
Commit
5c7d89e
1 Parent(s): cdd06a6
Files changed (3) hide show
  1. README.md +33 -0
  2. adapter_config.json +25 -0
  3. adapter_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ datasets:
4
+ - EleutherAI/wikitext_document_level
5
+ language:
6
+ - en
7
+ ---
8
+
9
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
10
+
11
+ LLaMA 33b finetuned on `wikitext_document_level` with a combination of both linear and NTK-aware ROPE scaling.
12
+
13
+ Trained with alpha=4, scale=2.
14
+
15
+ <img src="perplexity.png" alt="Perplexity Graph" />
16
+
17
+ ## Training procedure
18
+
19
+
20
+ The following `bitsandbytes` quantization config was used during training:
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: True
29
+ - bnb_4bit_compute_dtype: bfloat16
30
+ ### Framework versions
31
+
32
+
33
+ - PEFT 0.4.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "huggyllama/llama-30b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": null,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "layers_pattern": null,
8
+ "layers_to_transform": null,
9
+ "lora_alpha": 128,
10
+ "lora_dropout": 0.05,
11
+ "modules_to_save": null,
12
+ "peft_type": "LORA",
13
+ "r": 64,
14
+ "revision": null,
15
+ "target_modules": [
16
+ "o_proj",
17
+ "gate_proj",
18
+ "v_proj",
19
+ "q_proj",
20
+ "k_proj",
21
+ "up_proj",
22
+ "down_proj"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c5330ea8267a9a608db609ab12856711e2d3bd86a38a9944a28b810674be50
3
+ size 1950654765