Hugging Face's logo

mradermacher
/
tulu-v1-llama2-70b-GGUF

Transformers
GGUF
English
Inference Endpoints
Model card Files Community
mradermacher commited on
Commit
090ae13
•
1 Parent(s): c02af26

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -2
README.md CHANGED
@@ -16,9 +16,8 @@ quantized_by: mradermacher
16
  <!-- ### vocab_type: -->
17
  static quants of https://huggingface.co/allenai/tulu-v1-llama2-70b
18
 
19
-
20
  <!-- provided-files -->
21
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
22
  ## Usage
23
 
24
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -31,8 +30,19 @@ more details, including on how to concatenate multi-part files.
31
 
32
  | Link | Type | Size/GB | Notes |
33
  |:-----|:-----|--------:|:------|
 
 
34
  | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
 
 
 
 
 
35
  | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
 
 
 
 
36
  | [PART 1](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
37
 
38
 
 
16
  <!-- ### vocab_type: -->
17
  static quants of https://huggingface.co/allenai/tulu-v1-llama2-70b
18
 
 
19
  <!-- provided-files -->
20
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/tulu-v1-llama2-70b-i1-GGUF
21
  ## Usage
22
 
23
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
30
 
31
  | Link | Type | Size/GB | Notes |
32
  |:-----|:-----|--------:|:------|
33
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q2_K.gguf) | Q2_K | 25.6 | |
34
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.IQ3_XS.gguf) | IQ3_XS | 28.4 | |
35
  | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.IQ3_S.gguf) | IQ3_S | 30.0 | beats Q3_K* |
36
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q3_K_S.gguf) | Q3_K_S | 30.0 | |
37
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.IQ3_M.gguf) | IQ3_M | 31.0 | |
38
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q3_K_M.gguf) | Q3_K_M | 33.4 | lower quality |
39
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q3_K_L.gguf) | Q3_K_L | 36.2 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.IQ4_XS.gguf) | IQ4_XS | 37.3 | |
41
  | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q4_K_S.gguf) | Q4_K_S | 39.3 | fast, recommended |
42
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q4_K_M.gguf) | Q4_K_M | 41.5 | fast, recommended |
43
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q5_K_S.gguf) | Q5_K_S | 47.6 | |
44
+ | [GGUF](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q5_K_M.gguf) | Q5_K_M | 48.9 | |
45
+ | [PART 1](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q6_K.gguf.part2of2) | Q6_K | 56.7 | very good quality |
46
  | [PART 1](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/tulu-v1-llama2-70b-GGUF/resolve/main/tulu-v1-llama2-70b.Q8_0.gguf.part2of2) | Q8_0 | 73.4 | fast, best quality |
47
 
48