Hugging Face's logo

bullerwins
/
Reflection-Llama-3.1-70B-GGUF

Text Generation
GGUF
Inference Endpoints
conversational
Model card Files Community
1
bullerwins commited on
Commit
f82e54a
•
1 Parent(s): 71e1acc

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. .gitattributes +4 -0
  2. README.md +1 -9
  3. Reflection-70B-Q6_K-00001-of-00002.gguf +3 -0
  4. Reflection-70B-Q6_K-00002-of-00002.gguf +3 -0
  5. Reflection-70B-Q8_0-00001-of-00002.gguf +3 -0
  6. Reflection-70B-Q8_0-00002-of-00002.gguf +3 -0
.gitattributes CHANGED
@@ -41,3 +41,7 @@ Reflection-70B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
  Reflection-70B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
  Reflection-70B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
  Reflection-70B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
41
  Reflection-70B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
42
  Reflection-70B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
  Reflection-70B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Reflection-70B-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Reflection-70B-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Reflection-70B-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Reflection-70B-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,16 +1,8 @@
1
  ---
2
  license: llama3.1
3
- base_model: mattshumer/Reflection-Llama-3.1-70B
4
  pipeline_tag: text-generation
5
  ---
6
-
7
- GGUF quantized version with llama.cpp
8
-
9
- It includes the fixes to the vocab and tokenizer from 06/09/2024
10
-
11
- Original model [mattshumer/Reflection-Llama-3.1-70B](https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B)
12
-
13
-
14
  # Reflection Llama-3.1 70B
15
 
16
  **Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.**
 
1
  ---
2
  license: llama3.1
3
+ base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
4
  pipeline_tag: text-generation
5
  ---
 
 
 
 
 
 
 
 
6
  # Reflection Llama-3.1 70B
7
 
8
  **Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.**
Reflection-70B-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e741b8ceccba42115af3dafa60347efcbf9547eab27a304d44967c3e398d63
3
+ size 44900299360
Reflection-70B-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:323059d4fe7078f50d68986d4cac5a10ae2791ac9df62ce6e40488d83e2ad93d
3
+ size 12987925120
Reflection-70B-Q8_0-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef108f9f98059531f01dfe232d71473144e21a1066f368f8fad135b923e6f2ca
3
+ size 44764922304
Reflection-70B-Q8_0-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72385d1c11127664799e6f555831cf94a8fc09bd30656a52667b1842cbb10fff
3
+ size 30210232352