Hugging Face's logo

tensorblock
/
Llama-3-8B-ProLong-64k-Base-GGUF

GGUF
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
7515ac3
•
1 Parent(s): 70a10f1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -25,8 +25,16 @@ This repo contains GGUF format model files for [princeton-nlp/Llama-3-8B-ProLong
25
 
26
  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).
27
 
 
 
 
 
 
 
 
28
  ## Prompt template
29
 
 
30
  ```
31
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
32
 
@@ -39,18 +47,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
39
 
40
  | Filename | Quant type | File Size | Description |
41
  | -------- | ---------- | --------- | ----------- |
42
- | [Llama-3-8B-ProLong-64k-Base-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
43
- | [Llama-3-8B-ProLong-64k-Base-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
44
- | [Llama-3-8B-ProLong-64k-Base-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
45
- | [Llama-3-8B-ProLong-64k-Base-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
46
- | [Llama-3-8B-ProLong-64k-Base-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
47
- | [Llama-3-8B-ProLong-64k-Base-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
48
- | [Llama-3-8B-ProLong-64k-Base-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
49
- | [Llama-3-8B-ProLong-64k-Base-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
50
- | [Llama-3-8B-ProLong-64k-Base-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
51
- | [Llama-3-8B-ProLong-64k-Base-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
52
- | [Llama-3-8B-ProLong-64k-Base-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
53
- | [Llama-3-8B-ProLong-64k-Base-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/tree/main/Llama-3-8B-ProLong-64k-Base-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
54
 
55
 
56
  ## Downloading instruction
 
25
 
26
  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).
27
 
28
+
29
+ <div style="text-align: left; margin: 20px 0;">
30
+ <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;">
31
+ Run them on the TensorBlock client using your local machine ↗
32
+ </a>
33
+ </div>
34
+
35
  ## Prompt template
36
 
37
+
38
  ```
39
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
40
 
 
47
 
48
  | Filename | Quant type | File Size | Description |
49
  | -------- | ---------- | --------- | ----------- |
50
+ | [Llama-3-8B-ProLong-64k-Base-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
51
+ | [Llama-3-8B-ProLong-64k-Base-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
52
+ | [Llama-3-8B-ProLong-64k-Base-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
53
+ | [Llama-3-8B-ProLong-64k-Base-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
54
+ | [Llama-3-8B-ProLong-64k-Base-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
55
+ | [Llama-3-8B-ProLong-64k-Base-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
56
+ | [Llama-3-8B-ProLong-64k-Base-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
57
+ | [Llama-3-8B-ProLong-64k-Base-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
58
+ | [Llama-3-8B-ProLong-64k-Base-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
59
+ | [Llama-3-8B-ProLong-64k-Base-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
60
+ | [Llama-3-8B-ProLong-64k-Base-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
61
+ | [Llama-3-8B-ProLong-64k-Base-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-8B-ProLong-64k-Base-GGUF/blob/main/Llama-3-8B-ProLong-64k-Base-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
62
 
63
 
64
  ## Downloading instruction