|
--- |
|
license: apache-2.0 |
|
--- |
|
# SOLAR-10.7B-Instruct-v1.0-uncensored |
|
|
|
## Description |
|
This repo contains GGUF format model files for SOLAR-10.7B-Instruct-v1.0-uncensored. |
|
|
|
## Files Provided |
|
| Name | Quant | Bits | File Size | Remark | |
|
| ------------------------------------------------- | ------- | ---- | --------- | -------------------------------- | |
|
| solar-10.7b-instruct-v1.0-uncensored.IQ3_XXS.gguf | IQ3_XXS | 3 | 4.44 GB | 3.06 bpw quantization | |
|
| solar-10.7b-instruct-v1.0-uncensored.IQ3_S.gguf | IQ3_S | 3 | 4.69 GB | 3.44 bpw quantization | |
|
| solar-10.7b-instruct-v1.0-uncensored.IQ3_M.gguf | IQ3_M | 3 | 4.85 GB | 3.66 bpw quantization mix | |
|
| solar-10.7b-instruct-v1.0-uncensored.Q4_0.gguf | Q4_0 | 4 | 6.07 GB | 3.56G, +0.2166 ppl | |
|
| solar-10.7b-instruct-v1.0-uncensored.IQ4_NL.gguf | IQ4_NL | 4 | 6.14 GB | 4.25 bpw non-linear quantization | |
|
| solar-10.7b-instruct-v1.0-uncensored.Q4_K_M.gguf | Q4_K_M | 4 | 6.46 GB | 3.80G, +0.0532 ppl | |
|
| solar-10.7b-instruct-v1.0-uncensored.Q5_K_M.gguf | Q5_K_M | 5 | 7.60 GB | 4.45G, +0.0122 ppl | |
|
| solar-10.7b-instruct-v1.0-uncensored.Q6_K.gguf | Q6_K | 6 | 8.81 GB | 5.15G, +0.0008 ppl | |
|
| solar-10.7b-instruct-v1.0-uncensored.Q8_0.gguf | Q8_0 | 8 | 11.40 GB | 6.70G, +0.0004 ppl | |
|
|
|
## Parameters |
|
| path | type | architecture | rope_theta | sliding_win | max_pos_embed | |
|
| -------------------------------------------- | ----- | ---------------- | ---------- | ----------- | ------------- | |
|
| w4r10ck/SOLAR-10.7B-Instruct-v1.0-uncensored | llama | LlamaForCausalLM | 10000.0 | null | 4096 | |
|
|
|
|
|
# Original Model Card |
|
|
|
--- |
|
license: apache-2.0 |
|
--- |
|
|
|
[upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) finetuned on [unalignment/toxic-dpo-v0.1](https://huggingface.co/datasets/unalignment/toxic-dpo-v0.1) |
|
|
