Views
No views yet
| Name | Quant method | Size |
|---|---|---|
| archangel_sft_llama7b.Q2_K.gguf | Q2_K | 2.36GB |
| archangel_sft_llama7b.IQ3_XS.gguf | IQ3_XS | 2.6GB |
| archangel_sft_llama7b.IQ3_S.gguf | IQ3_S | 2.75GB |
| archangel_sft_llama7b.Q3_K_S.gguf | Q3_K_S | 2.75GB |
| archangel_sft_llama7b.IQ3_M.gguf | IQ3_M | 2.9GB |
| archangel_sft_llama7b.Q3_K.gguf | Q3_K | 3.07GB |
| archangel_sft_llama7b.Q3_K_M.gguf | Q3_K_M | 3.07GB |
| archangel_sft_llama7b.Q3_K_L.gguf | Q3_K_L | 3.35GB |
| archangel_sft_llama7b.IQ4_XS.gguf | IQ4_XS | 3.4GB |
| archangel_sft_llama7b.Q4_0.gguf | Q4_0 | 3.56GB |
| archangel_sft_llama7b.IQ4_NL.gguf | IQ4_NL | 3.58GB |
| archangel_sft_llama7b.Q4_K_S.gguf | Q4_K_S | 3.59GB |
| archangel_sft_llama7b.Q4_K.gguf | Q4_K | 3.8GB |
| archangel_sft_llama7b.Q4_K_M.gguf | Q4_K_M | 3.8GB |
| archangel_sft_llama7b.Q4_1.gguf | Q4_1 | 3.95GB |
| archangel_sft_llama7b.Q5_0.gguf | Q5_0 | 4.33GB |
| archangel_sft_llama7b.Q5_K_S.gguf | Q5_K_S | 4.33GB |
| archangel_sft_llama7b.Q5_K.gguf | Q5_K | 4.45GB |
| archangel_sft_llama7b.Q5_K_M.gguf | Q5_K_M | 4.45GB |
| archangel_sft_llama7b.Q5_1.gguf | Q5_1 | 4.72GB |
| archangel_sft_llama7b.Q6_K.gguf | Q6_K | 5.15GB |
| archangel_sft_llama7b.Q8_0.gguf | Q8_0 | 6.67GB |
<|user|> corresponds to the human's role and <|assistant|> corresponds to the LLM's role.
The human should speak first:<|user|>
Hi! I'm looking for a cake recipe.
<|assistant|>
What kind of cake?
<|user|>
Chocolate cake.
<|assistant|><|good|> and <|bad|> included in the embeddings.
To generate with these control tokens in the context, postpend either to the prompt.@techreport{ethayarajh2023halos,
author = {Ethayarajh, Kawin and Xu, Winnie, and Jurafsky, Dan and Kiela, Douwe},
title = {Human-Centered Loss Functions (HALOs)},
institution = {Contextual AI},
note = {https://github.com/ContextualAI/HALOs/blob/main/assets/report.pdf},
year = {2023},
}