YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Quantization made by Richard Erkhov.
Qwen2-0.5B-fncl - GGUF
- Model creator: https://huggingface.co/haripritam/
- Original model: https://huggingface.co/haripritam/Qwen2-0.5B-fncl/
Name | Quant method | Size |
---|---|---|
Qwen2-0.5B-fncl.Q2_K.gguf | Q2_K | 0.32GB |
Qwen2-0.5B-fncl.IQ3_XS.gguf | IQ3_XS | 0.32GB |
Qwen2-0.5B-fncl.IQ3_S.gguf | IQ3_S | 0.32GB |
Qwen2-0.5B-fncl.Q3_K_S.gguf | Q3_K_S | 0.32GB |
Qwen2-0.5B-fncl.IQ3_M.gguf | IQ3_M | 0.32GB |
Qwen2-0.5B-fncl.Q3_K.gguf | Q3_K | 0.33GB |
Qwen2-0.5B-fncl.Q3_K_M.gguf | Q3_K_M | 0.33GB |
Qwen2-0.5B-fncl.Q3_K_L.gguf | Q3_K_L | 0.34GB |
Qwen2-0.5B-fncl.IQ4_XS.gguf | IQ4_XS | 0.33GB |
Qwen2-0.5B-fncl.Q4_0.gguf | Q4_0 | 0.33GB |
Qwen2-0.5B-fncl.IQ4_NL.gguf | IQ4_NL | 0.33GB |
Qwen2-0.5B-fncl.Q4_K_S.gguf | Q4_K_S | 0.36GB |
Qwen2-0.5B-fncl.Q4_K.gguf | Q4_K | 0.37GB |
Qwen2-0.5B-fncl.Q4_K_M.gguf | Q4_K_M | 0.37GB |
Qwen2-0.5B-fncl.Q4_1.gguf | Q4_1 | 0.35GB |
Qwen2-0.5B-fncl.Q5_0.gguf | Q5_0 | 0.37GB |
Qwen2-0.5B-fncl.Q5_K_S.gguf | Q5_K_S | 0.38GB |
Qwen2-0.5B-fncl.Q5_K.gguf | Q5_K | 0.39GB |
Qwen2-0.5B-fncl.Q5_K_M.gguf | Q5_K_M | 0.39GB |
Qwen2-0.5B-fncl.Q5_1.gguf | Q5_1 | 0.39GB |
Qwen2-0.5B-fncl.Q6_K.gguf | Q6_K | 0.47GB |
Qwen2-0.5B-fncl.Q8_0.gguf | Q8_0 | 0.49GB |
Original model description:
license: apache-2.0 datasets: - haripritam/function-calling-alpaca
Works better than expected. LORA adapters are merged with Qwen/Qwen2-0.5B not the instruct version but somehow some responses are like instruct ???
- Downloads last month
- 18