Downloads · 30 days
12
22% of all-time downloads
llama-2-13b-chat-hf
MRNH/llama-2-13b-chat-hf
llama-2-13b-chat-hf is a text generation model from MRNH. Use it when you need the model to write or continue text. It is set up for peft.
The following bitsandbytes quantization config was used during training: - quantmethod: QuantizationMethod.BITSANDBYTES - loadin8bit: False - loadin4bit: True - llmint8threshold: 6.0 - llmint8skipmodules: None - llmin…
All-time downloads
55
Public
Repo size
52.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin26.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Model type
- llama
- Access
- Public
- Created
- Oct 1, 2023
- Updated
- Oct 17, 2023
- SHA
- cfba2126
Try a prompt
Model card
From the Hugging Face model README
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
The following bitsandbytes quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
-
PEFT 0.5.0
-
PEFT 0.5.0
- Task
- Text Generation
- Library
- peft
- Type
- llama
- Created
- Oct 1, 2023
- Updated
- Oct 17, 2023