Hugging Face's logo

tensorblock
/
Yi-6B-Infinity-Chat-GGUF

GGUF
TensorBlock
GGUF
Eval Results
conversational
Model card Files Community
morriszms commited on
Commit
a4ef3cb
•
1 Parent(s): 977da0e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -127,8 +127,16 @@ This repo contains GGUF format model files for [Walmart-the-bag/Yi-6B-Infinity-C
127
 
128
  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).
129
 
 
 
 
 
 
 
 
130
  ## Prompt template
131
 
 
132
  ```
133
  <|im_start|>system
134
  {system_prompt}<|im_end|>
@@ -141,18 +149,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
141
 
142
  | Filename | Quant type | File Size | Description |
143
  | -------- | ---------- | --------- | ----------- |
144
- | [Yi-6B-Infinity-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q2_K.gguf) | Q2_K | 2.177 GB | smallest, significant quality loss - not recommended for most purposes |
145
- | [Yi-6B-Infinity-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q3_K_S.gguf) | Q3_K_S | 2.523 GB | very small, high quality loss |
146
- | [Yi-6B-Infinity-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q3_K_M.gguf) | Q3_K_M | 2.788 GB | very small, high quality loss |
147
- | [Yi-6B-Infinity-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q3_K_L.gguf) | Q3_K_L | 3.015 GB | small, substantial quality loss |
148
- | [Yi-6B-Infinity-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q4_0.gguf) | Q4_0 | 3.241 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
149
- | [Yi-6B-Infinity-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q4_K_S.gguf) | Q4_K_S | 3.263 GB | small, greater quality loss |
150
- | [Yi-6B-Infinity-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q4_K_M.gguf) | Q4_K_M | 3.422 GB | medium, balanced quality - recommended |
151
- | [Yi-6B-Infinity-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q5_0.gguf) | Q5_0 | 3.916 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
152
- | [Yi-6B-Infinity-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q5_K_S.gguf) | Q5_K_S | 3.916 GB | large, low quality loss - recommended |
153
- | [Yi-6B-Infinity-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q5_K_M.gguf) | Q5_K_M | 4.009 GB | large, very low quality loss - recommended |
154
- | [Yi-6B-Infinity-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q6_K.gguf) | Q6_K | 4.633 GB | very large, extremely low quality loss |
155
- | [Yi-6B-Infinity-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/tree/main/Yi-6B-Infinity-Chat-Q8_0.gguf) | Q8_0 | 6.000 GB | very large, extremely low quality loss - not recommended |
156
 
157
 
158
  ## Downloading instruction
 
127
 
128
  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).
129
 
130
+
131
+ <div style="text-align: left; margin: 20px 0;">
132
+ <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;">
133
+ Run them on the TensorBlock client using your local machine ↗
134
+ </a>
135
+ </div>
136
+
137
  ## Prompt template
138
 
139
+
140
  ```
141
  <|im_start|>system
142
  {system_prompt}<|im_end|>
 
149
 
150
  | Filename | Quant type | File Size | Description |
151
  | -------- | ---------- | --------- | ----------- |
152
+ | [Yi-6B-Infinity-Chat-Q2_K.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q2_K.gguf) | Q2_K | 2.177 GB | smallest, significant quality loss - not recommended for most purposes |
153
+ | [Yi-6B-Infinity-Chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q3_K_S.gguf) | Q3_K_S | 2.523 GB | very small, high quality loss |
154
+ | [Yi-6B-Infinity-Chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q3_K_M.gguf) | Q3_K_M | 2.788 GB | very small, high quality loss |
155
+ | [Yi-6B-Infinity-Chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q3_K_L.gguf) | Q3_K_L | 3.015 GB | small, substantial quality loss |
156
+ | [Yi-6B-Infinity-Chat-Q4_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q4_0.gguf) | Q4_0 | 3.241 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
157
+ | [Yi-6B-Infinity-Chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q4_K_S.gguf) | Q4_K_S | 3.263 GB | small, greater quality loss |
158
+ | [Yi-6B-Infinity-Chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q4_K_M.gguf) | Q4_K_M | 3.422 GB | medium, balanced quality - recommended |
159
+ | [Yi-6B-Infinity-Chat-Q5_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q5_0.gguf) | Q5_0 | 3.916 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
160
+ | [Yi-6B-Infinity-Chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q5_K_S.gguf) | Q5_K_S | 3.916 GB | large, low quality loss - recommended |
161
+ | [Yi-6B-Infinity-Chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q5_K_M.gguf) | Q5_K_M | 4.009 GB | large, very low quality loss - recommended |
162
+ | [Yi-6B-Infinity-Chat-Q6_K.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q6_K.gguf) | Q6_K | 4.633 GB | very large, extremely low quality loss |
163
+ | [Yi-6B-Infinity-Chat-Q8_0.gguf](https://huggingface.co/tensorblock/Yi-6B-Infinity-Chat-GGUF/blob/main/Yi-6B-Infinity-Chat-Q8_0.gguf) | Q8_0 | 6.000 GB | very large, extremely low quality loss - not recommended |
164
 
165
 
166
  ## Downloading instruction