Hugging Face's logo

tensorblock
/
Llama-3.2-3B-Instruct-uncensored-GGUF

Transformers
GGUF
TensorBlock
GGUF
conversational
Model card Files Community
morriszms commited on
Commit
dd7b5fd
·
verified ·
1 Parent(s): 99538a3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -23,8 +23,16 @@ This repo contains GGUF format model files for [chuanli11/Llama-3.2-3B-Instruct-
23
 
24
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
25
 
 
 
 
 
 
 
 
26
  ## Prompt template
27
 
 
28
  ```
29
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
30
 
@@ -40,18 +48,18 @@ Today Date: 10 Nov 2024
40
 
41
  | Filename | Quant type | File Size | Description |
42
  | -------- | ---------- | --------- | ----------- |
43
- | [Llama-3.2-3B-Instruct-uncensored-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q2_K.gguf) | Q2_K | 1.391 GB | smallest, significant quality loss - not recommended for most purposes |
44
- | [Llama-3.2-3B-Instruct-uncensored-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q3_K_S.gguf) | Q3_K_S | 1.595 GB | very small, high quality loss |
45
- | [Llama-3.2-3B-Instruct-uncensored-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q3_K_M.gguf) | Q3_K_M | 1.729 GB | very small, high quality loss |
46
- | [Llama-3.2-3B-Instruct-uncensored-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q3_K_L.gguf) | Q3_K_L | 1.848 GB | small, substantial quality loss |
47
- | [Llama-3.2-3B-Instruct-uncensored-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q4_0.gguf) | Q4_0 | 1.992 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
48
- | [Llama-3.2-3B-Instruct-uncensored-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q4_K_S.gguf) | Q4_K_S | 2.002 GB | small, greater quality loss |
49
- | [Llama-3.2-3B-Instruct-uncensored-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q4_K_M.gguf) | Q4_K_M | 2.087 GB | medium, balanced quality - recommended |
50
- | [Llama-3.2-3B-Instruct-uncensored-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q5_0.gguf) | Q5_0 | 2.366 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
51
- | [Llama-3.2-3B-Instruct-uncensored-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q5_K_S.gguf) | Q5_K_S | 2.366 GB | large, low quality loss - recommended |
52
- | [Llama-3.2-3B-Instruct-uncensored-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q5_K_M.gguf) | Q5_K_M | 2.415 GB | large, very low quality loss - recommended |
53
- | [Llama-3.2-3B-Instruct-uncensored-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q6_K.gguf) | Q6_K | 2.763 GB | very large, extremely low quality loss |
54
- | [Llama-3.2-3B-Instruct-uncensored-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/tree/main/Llama-3.2-3B-Instruct-uncensored-Q8_0.gguf) | Q8_0 | 3.577 GB | very large, extremely low quality loss - not recommended |
55
 
56
 
57
  ## Downloading instruction
 
23
 
24
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
25
 
26
+
27
+ <div style="text-align: left; margin: 20px 0;">
28
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
29
+ Run them on the TensorBlock client using your local machine ↗
30
+ </a>
31
+ </div>
32
+
33
  ## Prompt template
34
 
35
+
36
  ```
37
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
38
 
 
48
 
49
  | Filename | Quant type | File Size | Description |
50
  | -------- | ---------- | --------- | ----------- |
51
+ | [Llama-3.2-3B-Instruct-uncensored-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q2_K.gguf) | Q2_K | 1.391 GB | smallest, significant quality loss - not recommended for most purposes |
52
+ | [Llama-3.2-3B-Instruct-uncensored-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q3_K_S.gguf) | Q3_K_S | 1.595 GB | very small, high quality loss |
53
+ | [Llama-3.2-3B-Instruct-uncensored-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q3_K_M.gguf) | Q3_K_M | 1.729 GB | very small, high quality loss |
54
+ | [Llama-3.2-3B-Instruct-uncensored-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q3_K_L.gguf) | Q3_K_L | 1.848 GB | small, substantial quality loss |
55
+ | [Llama-3.2-3B-Instruct-uncensored-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q4_0.gguf) | Q4_0 | 1.992 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
56
+ | [Llama-3.2-3B-Instruct-uncensored-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q4_K_S.gguf) | Q4_K_S | 2.002 GB | small, greater quality loss |
57
+ | [Llama-3.2-3B-Instruct-uncensored-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q4_K_M.gguf) | Q4_K_M | 2.087 GB | medium, balanced quality - recommended |
58
+ | [Llama-3.2-3B-Instruct-uncensored-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q5_0.gguf) | Q5_0 | 2.366 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
59
+ | [Llama-3.2-3B-Instruct-uncensored-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q5_K_S.gguf) | Q5_K_S | 2.366 GB | large, low quality loss - recommended |
60
+ | [Llama-3.2-3B-Instruct-uncensored-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q5_K_M.gguf) | Q5_K_M | 2.415 GB | large, very low quality loss - recommended |
61
+ | [Llama-3.2-3B-Instruct-uncensored-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q6_K.gguf) | Q6_K | 2.763 GB | very large, extremely low quality loss |
62
+ | [Llama-3.2-3B-Instruct-uncensored-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.2-3B-Instruct-uncensored-GGUF/blob/main/Llama-3.2-3B-Instruct-uncensored-Q8_0.gguf) | Q8_0 | 3.577 GB | very large, extremely low quality loss - not recommended |
63
 
64
 
65
  ## Downloading instruction