Hugging Face's logo

cognitivecomputations
/
minotaur-llama2-13b-qlora

PEFT
Eval Results
Model card Files Community
3
ehartford commited on
Commit
0c0d612
•
1 Parent(s): 6831655

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. README.md +20 -0
  2. adapter_config.json +26 -0
  3. adapter_model.bin +3 -0
  4. adapter_model/README.md +20 -0
  5. adapter_model/adapter_config.json +26 -0
  6. adapter_model/adapter_model.bin +3 -0
  7. optimizer.pt +3 -0
  8. rng_state_0.pth +3 -0
  9. rng_state_1.pth +3 -0
  10. rng_state_2.pth +3 -0
  11. rng_state_3.pth +3 -0
  12. scheduler.pt +3 -0
  13. trainer_state.json +0 -0
  14. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TheBloke/Llama-2-13B-fp16",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "gate_proj",
18
+ "k_proj",
19
+ "down_proj",
20
+ "q_proj",
21
+ "o_proj",
22
+ "up_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caaff81135f4eca76c011894f79364b7ec9e3a2f28a0a8a02c6035c9517a0c4
3
+ size 1001592141
adapter_model/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: float32
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
adapter_model/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TheBloke/Llama-2-13B-fp16",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "gate_proj",
18
+ "k_proj",
19
+ "down_proj",
20
+ "q_proj",
21
+ "o_proj",
22
+ "up_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caaff81135f4eca76c011894f79364b7ec9e3a2f28a0a8a02c6035c9517a0c4
3
+ size 1001592141
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cde279d376ed4561a1bff1d3b5e165e1ce4545628f855f24e246cf11c22cc9
3
+ size 502330847
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23d2f7abe22bb3d68e2eb9a437351b0a1659a1ed0af886a5a0af2a286d25d531
3
+ size 17655
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5d0e1301552f439142a3d4dce745dc2e89548f4952989a3cffc83aa54205f2
3
+ size 17655
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e85dfc555753fb7c676954506451e91a3e2d19e7351d8d1e09f923bee1aec22
3
+ size 17655
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f31518223123dbf408bff993a00a05418e488e57cbea199d859da6ad5f4160
3
+ size 17655
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9d132263592de70745fac377e94c5060bf546346c0ded7556916ffa36279b4
3
+ size 627
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c923d223679a482fa4a45efe1e1448127e4117c5ad9b20386b89aef64da4b919
3
+ size 4027