Upload model
Browse files- README.md +56 -0
- adapter_config.json +19 -0
- adapter_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: True
|
| 9 |
+
- load_in_4bit: False
|
| 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: fp4
|
| 15 |
+
- bnb_4bit_use_double_quant: False
|
| 16 |
+
- bnb_4bit_compute_dtype: float32
|
| 17 |
+
|
| 18 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 19 |
+
- load_in_8bit: True
|
| 20 |
+
- load_in_4bit: False
|
| 21 |
+
- llm_int8_threshold: 6.0
|
| 22 |
+
- llm_int8_skip_modules: None
|
| 23 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 24 |
+
- llm_int8_has_fp16_weight: False
|
| 25 |
+
- bnb_4bit_quant_type: fp4
|
| 26 |
+
- bnb_4bit_use_double_quant: False
|
| 27 |
+
- bnb_4bit_compute_dtype: float32
|
| 28 |
+
|
| 29 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 30 |
+
- load_in_8bit: True
|
| 31 |
+
- load_in_4bit: False
|
| 32 |
+
- llm_int8_threshold: 6.0
|
| 33 |
+
- llm_int8_skip_modules: None
|
| 34 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 35 |
+
- llm_int8_has_fp16_weight: False
|
| 36 |
+
- bnb_4bit_quant_type: fp4
|
| 37 |
+
- bnb_4bit_use_double_quant: False
|
| 38 |
+
- bnb_4bit_compute_dtype: float32
|
| 39 |
+
|
| 40 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 41 |
+
- load_in_8bit: True
|
| 42 |
+
- load_in_4bit: False
|
| 43 |
+
- llm_int8_threshold: 6.0
|
| 44 |
+
- llm_int8_skip_modules: None
|
| 45 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 46 |
+
- llm_int8_has_fp16_weight: False
|
| 47 |
+
- bnb_4bit_quant_type: fp4
|
| 48 |
+
- bnb_4bit_use_double_quant: False
|
| 49 |
+
- bnb_4bit_compute_dtype: float32
|
| 50 |
+
### Framework versions
|
| 51 |
+
|
| 52 |
+
- PEFT 0.4.0.dev0
|
| 53 |
+
- PEFT 0.4.0.dev0
|
| 54 |
+
- PEFT 0.4.0.dev0
|
| 55 |
+
|
| 56 |
+
- PEFT 0.4.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "togethercomputer/RedPajama-INCITE-Base-3B-v1",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 16,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"query_key_value"
|
| 17 |
+
],
|
| 18 |
+
"task_type": "CAUSAL_LM"
|
| 19 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ea37b4b07edd9059f43091742801d7b7fac2e870ce4b8ebc88ac79aa1363779
|
| 3 |
+
size 10509233
|