Downloads · 30 days
0
llama-2-13b_code-alpaca-qlora-sft-en-sr
cminja/llama-2-13b_code-alpaca-qlora-sft-en-sr
llama-2-13b_code-alpaca-qlora-sft-en-sr is a machine learning model from cminja. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama2.
A full SFT of original 'llama-2-13bcode-alpaca' using a mix of English and Serbian instruction data.
Access
Public
Updated Jun 18, 2024
Repo size
501 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin501 MB · 100%
At a glance
- License
- llama2
- Access
- Public
- Created
- Jun 17, 2024
- Updated
- Jun 18, 2024
- SHA
- 1f0215e9
Model card
From the Hugging Face model README
A full SFT of original 'llama-2-13b_code-alpaca' using a mix of English and Serbian instruction data.
The following bitsandbytes quantization config was used during training: 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: True bnb_4bit_compute_dtype: bfloat16
The following bitsandbytes quantization config was used during training: 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: True bnb_4bit_compute_dtype: bfloat16
The following bitsandbytes quantization config was used during training: 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: True bnb_4bit_compute_dtype: bfloat16
Framework versions PEFT 0.5.0.dev0
- License
- llama2
- Created
- Jun 17, 2024
- Updated
- Jun 18, 2024