Hugging Face's logo

tensorblock
/
NeuralLLaMa-3-8b-ORPO-v0.3-GGUF

GGUF
TensorBlock
GGUF
Eval Results
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
4af87a1
•
1 Parent(s): 9915f69

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -12
README.md CHANGED
@@ -128,8 +128,16 @@ This repo contains GGUF format model files for [Kukedlc/NeuralLLaMa-3-8b-ORPO-v0
128
 
129
  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).
130
 
 
 
 
 
 
 
 
131
  ## Prompt template
132
 
 
133
  ```
134
  <|im_start|>system
135
  {system_prompt}<|im_end|>
@@ -142,18 +150,18 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
142
 
143
  | Filename | Quant type | File Size | Description |
144
  | -------- | ---------- | --------- | ----------- |
145
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
146
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
147
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
148
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
149
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
150
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
151
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
152
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
153
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
154
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
155
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
156
- | [NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/tree/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
157
 
158
 
159
  ## Downloading instruction
 
128
 
129
  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).
130
 
131
+
132
+ <div style="text-align: left; margin: 20px 0;">
133
+ <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;">
134
+ Run them on the TensorBlock client using your local machine ↗
135
+ </a>
136
+ </div>
137
+
138
  ## Prompt template
139
 
140
+
141
  ```
142
  <|im_start|>system
143
  {system_prompt}<|im_end|>
 
150
 
151
  | Filename | Quant type | File Size | Description |
152
  | -------- | ---------- | --------- | ----------- |
153
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
154
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
155
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
156
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
157
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
158
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
159
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
160
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
161
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
162
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
163
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
164
+ | [NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf](https://huggingface.co/tensorblock/NeuralLLaMa-3-8b-ORPO-v0.3-GGUF/blob/main/NeuralLLaMa-3-8b-ORPO-v0.3-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
165
 
166
 
167
  ## Downloading instruction