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.
eleuther-pythia70m-hh-dpo - GGUF
- Model creator: https://huggingface.co/lomahony/
- Original model: https://huggingface.co/lomahony/eleuther-pythia70m-hh-dpo/
| Name | Quant method | Size |
|---|---|---|
| eleuther-pythia70m-hh-dpo.Q2_K.gguf | Q2_K | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q3_K_S.gguf | Q3_K_S | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q3_K.gguf | Q3_K | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q3_K_M.gguf | Q3_K_M | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q3_K_L.gguf | Q3_K_L | 0.04GB |
| eleuther-pythia70m-hh-dpo.IQ4_XS.gguf | IQ4_XS | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q4_0.gguf | Q4_0 | 0.04GB |
| eleuther-pythia70m-hh-dpo.IQ4_NL.gguf | IQ4_NL | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q4_K_S.gguf | Q4_K_S | 0.04GB |
| eleuther-pythia70m-hh-dpo.Q4_K.gguf | Q4_K | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q4_K_M.gguf | Q4_K_M | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q4_1.gguf | Q4_1 | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q5_0.gguf | Q5_0 | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q5_K_S.gguf | Q5_K_S | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q5_K.gguf | Q5_K | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q5_K_M.gguf | Q5_K_M | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q5_1.gguf | Q5_1 | 0.05GB |
| eleuther-pythia70m-hh-dpo.Q6_K.gguf | Q6_K | 0.06GB |
| eleuther-pythia70m-hh-dpo.Q8_0.gguf | Q8_0 | 0.07GB |
Original model description:
language: - en tags: - pytorch - causal-lm - pythia license: apache-2.0 datasets: - Anthropic/hh-rlhf
Pythia-70m supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch (sft-model), before DPO (paper) with same dataset for 1 epoch.
Benchmark evaluations included in repo done using lm-evaluation-harness.
See Pythia-70m for original model details (paper).
- Downloads last month
- 309