Hugging Face's logo

mradermacher
/
OpenBioLLM-Llama3-70B-i1-GGUF

Transformers
GGUF
English
llama-3
llama
Mixtral
instruct
finetune
chatml
DPO
RLHF
gpt4
distillation
heathcare
medical
clinical
med
lifescience
Pharmaceutical
Pharma
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
f5d62f0
•
1 Parent(s): bce79e3

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -40,7 +40,7 @@ more details, including on how to concatenate multi-part files.
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
43
- | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | for the desperate |
44
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
45
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
46
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
@@ -61,7 +61,6 @@ more details, including on how to concatenate multi-part files.
61
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.1 | |
62
  | [PART 1](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
63
 
64
-
65
  Here is a handy graph by ikawrakow comparing some lower-quality quant
66
  types (lower is better):
67
 
 
40
  | Link | Type | Size/GB | Notes |
41
  |:-----|:-----|--------:|:------|
42
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
43
+ | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
44
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
45
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
46
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
 
61
  | [GGUF](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.1 | |
62
  | [PART 1](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/OpenBioLLM-Llama3-70B-i1-GGUF/resolve/main/OpenBioLLM-Llama3-70B.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
63
 
 
64
  Here is a handy graph by ikawrakow comparing some lower-quality quant
65
  types (lower is better):
66