Hugging Face's logo

tensorblock
/
Phi-3.5-mini-ITA-GGUF

Text Generation
Transformers
GGUF
Italian
English
trl
phi3
spectrum
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
2a532f2
•
1 Parent(s): 3cb79be

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -34,8 +34,16 @@ This repo contains GGUF format model files for [anakin87/Phi-3.5-mini-ITA](https
34
 
35
  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).
36
 
 
 
 
 
 
 
 
37
  ## Prompt template
38
 
 
39
  ```
40
  <|system|>
41
  {system_prompt}<|end|>
@@ -48,18 +56,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
48
 
49
  | Filename | Quant type | File Size | Description |
50
  | -------- | ---------- | --------- | ----------- |
51
- | [Phi-3.5-mini-ITA-Q2_K.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q2_K.gguf) | Q2_K | 1.319 GB | smallest, significant quality loss - not recommended for most purposes |
52
- | [Phi-3.5-mini-ITA-Q3_K_S.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q3_K_S.gguf) | Q3_K_S | 1.566 GB | very small, high quality loss |
53
- | [Phi-3.5-mini-ITA-Q3_K_M.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q3_K_M.gguf) | Q3_K_M | 1.821 GB | very small, high quality loss |
54
- | [Phi-3.5-mini-ITA-Q3_K_L.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q3_K_L.gguf) | Q3_K_L | 1.944 GB | small, substantial quality loss |
55
- | [Phi-3.5-mini-ITA-Q4_0.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q4_0.gguf) | Q4_0 | 2.027 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
56
- | [Phi-3.5-mini-ITA-Q4_K_S.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q4_K_S.gguf) | Q4_K_S | 2.038 GB | small, greater quality loss |
57
- | [Phi-3.5-mini-ITA-Q4_K_M.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q4_K_M.gguf) | Q4_K_M | 2.229 GB | medium, balanced quality - recommended |
58
- | [Phi-3.5-mini-ITA-Q5_0.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q5_0.gguf) | Q5_0 | 2.460 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
59
- | [Phi-3.5-mini-ITA-Q5_K_S.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q5_K_S.gguf) | Q5_K_S | 2.460 GB | large, low quality loss - recommended |
60
- | [Phi-3.5-mini-ITA-Q5_K_M.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q5_K_M.gguf) | Q5_K_M | 2.622 GB | large, very low quality loss - recommended |
61
- | [Phi-3.5-mini-ITA-Q6_K.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q6_K.gguf) | Q6_K | 2.920 GB | very large, extremely low quality loss |
62
- | [Phi-3.5-mini-ITA-Q8_0.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/tree/main/Phi-3.5-mini-ITA-Q8_0.gguf) | Q8_0 | 3.782 GB | very large, extremely low quality loss - not recommended |
63
 
64
 
65
  ## Downloading instruction
 
34
 
35
  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).
36
 
37
+
38
+ <div style="text-align: left; margin: 20px 0;">
39
+ <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;">
40
+ Run them on the TensorBlock client using your local machine ↗
41
+ </a>
42
+ </div>
43
+
44
  ## Prompt template
45
 
46
+
47
  ```
48
  <|system|>
49
  {system_prompt}<|end|>
 
56
 
57
  | Filename | Quant type | File Size | Description |
58
  | -------- | ---------- | --------- | ----------- |
59
+ | [Phi-3.5-mini-ITA-Q2_K.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q2_K.gguf) | Q2_K | 1.319 GB | smallest, significant quality loss - not recommended for most purposes |
60
+ | [Phi-3.5-mini-ITA-Q3_K_S.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q3_K_S.gguf) | Q3_K_S | 1.566 GB | very small, high quality loss |
61
+ | [Phi-3.5-mini-ITA-Q3_K_M.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q3_K_M.gguf) | Q3_K_M | 1.821 GB | very small, high quality loss |
62
+ | [Phi-3.5-mini-ITA-Q3_K_L.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q3_K_L.gguf) | Q3_K_L | 1.944 GB | small, substantial quality loss |
63
+ | [Phi-3.5-mini-ITA-Q4_0.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q4_0.gguf) | Q4_0 | 2.027 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
64
+ | [Phi-3.5-mini-ITA-Q4_K_S.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q4_K_S.gguf) | Q4_K_S | 2.038 GB | small, greater quality loss |
65
+ | [Phi-3.5-mini-ITA-Q4_K_M.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q4_K_M.gguf) | Q4_K_M | 2.229 GB | medium, balanced quality - recommended |
66
+ | [Phi-3.5-mini-ITA-Q5_0.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q5_0.gguf) | Q5_0 | 2.460 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
67
+ | [Phi-3.5-mini-ITA-Q5_K_S.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q5_K_S.gguf) | Q5_K_S | 2.460 GB | large, low quality loss - recommended |
68
+ | [Phi-3.5-mini-ITA-Q5_K_M.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q5_K_M.gguf) | Q5_K_M | 2.622 GB | large, very low quality loss - recommended |
69
+ | [Phi-3.5-mini-ITA-Q6_K.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q6_K.gguf) | Q6_K | 2.920 GB | very large, extremely low quality loss |
70
+ | [Phi-3.5-mini-ITA-Q8_0.gguf](https://huggingface.co/tensorblock/Phi-3.5-mini-ITA-GGUF/blob/main/Phi-3.5-mini-ITA-Q8_0.gguf) | Q8_0 | 3.782 GB | very large, extremely low quality loss - not recommended |
71
 
72
 
73
  ## Downloading instruction