Hugging Face's logo

tensorblock
/
NeuralDaredevil-8B-abliterated-GGUF

GGUF
dpo
TensorBlock
GGUF
Eval Results
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
6e8b5a7
•
1 Parent(s): 5d573c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -129,8 +129,16 @@ This repo contains GGUF format model files for [mlabonne/NeuralDaredevil-8B-abli
129
 
130
  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).
131
 
 
 
 
 
 
 
 
132
  ## Prompt template
133
 
 
134
  ```
135
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
136
 
@@ -143,18 +151,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
143
 
144
  | Filename | Quant type | File Size | Description |
145
  | -------- | ---------- | --------- | ----------- |
146
- | [NeuralDaredevil-8B-abliterated-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
147
- | [NeuralDaredevil-8B-abliterated-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
148
- | [NeuralDaredevil-8B-abliterated-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
149
- | [NeuralDaredevil-8B-abliterated-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
150
- | [NeuralDaredevil-8B-abliterated-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
151
- | [NeuralDaredevil-8B-abliterated-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
152
- | [NeuralDaredevil-8B-abliterated-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
153
- | [NeuralDaredevil-8B-abliterated-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
154
- | [NeuralDaredevil-8B-abliterated-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
155
- | [NeuralDaredevil-8B-abliterated-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
156
- | [NeuralDaredevil-8B-abliterated-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
157
- | [NeuralDaredevil-8B-abliterated-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/tree/main/NeuralDaredevil-8B-abliterated-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
158
 
159
 
160
  ## Downloading instruction
 
129
 
130
  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).
131
 
132
+
133
+ <div style="text-align: left; margin: 20px 0;">
134
+ <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;">
135
+ Run them on the TensorBlock client using your local machine ↗
136
+ </a>
137
+ </div>
138
+
139
  ## Prompt template
140
 
141
+
142
  ```
143
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
144
 
 
151
 
152
  | Filename | Quant type | File Size | Description |
153
  | -------- | ---------- | --------- | ----------- |
154
+ | [NeuralDaredevil-8B-abliterated-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
155
+ | [NeuralDaredevil-8B-abliterated-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
156
+ | [NeuralDaredevil-8B-abliterated-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
157
+ | [NeuralDaredevil-8B-abliterated-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
158
+ | [NeuralDaredevil-8B-abliterated-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
159
+ | [NeuralDaredevil-8B-abliterated-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
160
+ | [NeuralDaredevil-8B-abliterated-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
161
+ | [NeuralDaredevil-8B-abliterated-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
162
+ | [NeuralDaredevil-8B-abliterated-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
163
+ | [NeuralDaredevil-8B-abliterated-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
164
+ | [NeuralDaredevil-8B-abliterated-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
165
+ | [NeuralDaredevil-8B-abliterated-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralDaredevil-8B-abliterated-GGUF/blob/main/NeuralDaredevil-8B-abliterated-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
166
 
167
 
168
  ## Downloading instruction