TheBlock commited on
Commit
781c73e
1 Parent(s): 24b18f0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +23 -25
README.md CHANGED
@@ -9,7 +9,7 @@ pipeline_tag: text-generation
9
  prompt_template: '<s>[INST] {prompt} [/INST]
10
 
11
  '
12
- quantized_by: TheBloke
13
  tags:
14
  - finetuned
15
  ---
@@ -18,17 +18,17 @@ tags:
18
  <!-- header start -->
19
  <!-- 200823 -->
20
  <div style="width: auto; margin-left: auto; margin-right: auto">
21
- <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
  </div>
23
  <div style="display: flex; justify-content: space-between; width: 100%;">
24
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
25
- <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
26
  </div>
27
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
28
- <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
29
  </div>
30
  </div>
31
- <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
32
  <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
33
  <!-- header end -->
34
 
@@ -66,9 +66,7 @@ Here is an incomplete list of clients and libraries that are known to support GG
66
  <!-- repositories-available start -->
67
  ## Repositories available
68
 
69
- * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-AWQ)
70
- * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ)
71
- * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF)
72
  * [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
73
  <!-- repositories-available end -->
74
 
@@ -112,18 +110,18 @@ Refer to the Provided Files table below to see what files use which methods, and
112
 
113
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
114
  | ---- | ---- | ---- | ---- | ---- | ----- |
115
- | [mistral-7b-instruct-v0.2.Q2_K.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
116
- | [mistral-7b-instruct-v0.2.Q3_K_S.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
117
- | [mistral-7b-instruct-v0.2.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
118
- | [mistral-7b-instruct-v0.2.Q3_K_L.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
119
- | [mistral-7b-instruct-v0.2.Q4_0.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
120
- | [mistral-7b-instruct-v0.2.Q4_K_S.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
121
- | [mistral-7b-instruct-v0.2.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
122
- | [mistral-7b-instruct-v0.2.Q5_0.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
123
- | [mistral-7b-instruct-v0.2.Q5_K_S.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
124
- | [mistral-7b-instruct-v0.2.Q5_K_M.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
125
- | [mistral-7b-instruct-v0.2.Q6_K.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
126
- | [mistral-7b-instruct-v0.2.Q8_0.gguf](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
127
 
128
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
129
 
@@ -144,7 +142,7 @@ The following clients/libraries will automatically download models for you, prov
144
 
145
  ### In `text-generation-webui`
146
 
147
- Under Download Model, you can enter the model repo: TheBloke/Mistral-7B-Instruct-v0.2-GGUF and below it, a specific filename to download, such as: mistral-7b-instruct-v0.2.Q4_K_M.gguf.
148
 
149
  Then click Download.
150
 
@@ -159,7 +157,7 @@ pip3 install huggingface-hub
159
  Then you can download any individual model file to the current directory, at high speed, with a command like this:
160
 
161
  ```shell
162
- huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
163
  ```
164
 
165
  <details>
@@ -168,7 +166,7 @@ huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instr
168
  You can also download multiple files at once with a pattern:
169
 
170
  ```shell
171
- huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
172
  ```
173
 
174
  For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
@@ -182,7 +180,7 @@ pip3 install hf_transfer
182
  And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
183
 
184
  ```shell
185
- HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
186
  ```
187
 
188
  Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
@@ -291,7 +289,7 @@ Here are guides on using llama-cpp-python and ctransformers with LangChain:
291
 
292
  For further support, and discussions on these models and AI in general, join us at:
293
 
294
- [TheBloke AI's Discord server](https://discord.gg/theblokeai)
295
 
296
  ## Thanks, and how to contribute
297
 
 
9
  prompt_template: '<s>[INST] {prompt} [/INST]
10
 
11
  '
12
+ quantized_by: TheBlock
13
  tags:
14
  - finetuned
15
  ---
 
18
  <!-- header start -->
19
  <!-- 200823 -->
20
  <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlockAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
  </div>
23
  <div style="display: flex; justify-content: space-between; width: 100%;">
24
  <div style="display: flex; flex-direction: column; align-items: flex-start;">
25
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/TheBlockai">Chat & support: TheBlock's Discord server</a></p>
26
  </div>
27
  <div style="display: flex; flex-direction: column; align-items: flex-end;">
28
+ <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlockAI">Want to contribute? TheBlock's Patreon page</a></p>
29
  </div>
30
  </div>
31
+ <div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBlock's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
32
  <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
33
  <!-- header end -->
34
 
 
66
  <!-- repositories-available start -->
67
  ## Repositories available
68
 
69
+ * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF)
 
 
70
  * [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
71
  <!-- repositories-available end -->
72
 
 
110
 
111
  | Name | Quant method | Bits | Size | Max RAM required | Use case |
112
  | ---- | ---- | ---- | ---- | ---- | ----- |
113
+ | [mistral-7b-instruct-v0.2.Q2_K.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q2_K.gguf) | Q2_K | 2 | 3.08 GB| 5.58 GB | smallest, significant quality loss - not recommended for most purposes |
114
+ | [mistral-7b-instruct-v0.2.Q3_K_S.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| 5.66 GB | very small, high quality loss |
115
+ | [mistral-7b-instruct-v0.2.Q3_K_M.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| 6.02 GB | very small, high quality loss |
116
+ | [mistral-7b-instruct-v0.2.Q3_K_L.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| 6.32 GB | small, substantial quality loss |
117
+ | [mistral-7b-instruct-v0.2.Q4_0.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| 6.61 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
118
+ | [mistral-7b-instruct-v0.2.Q4_K_S.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| 6.64 GB | small, greater quality loss |
119
+ | [mistral-7b-instruct-v0.2.Q4_K_M.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| 6.87 GB | medium, balanced quality - recommended |
120
+ | [mistral-7b-instruct-v0.2.Q5_0.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| 7.50 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
121
+ | [mistral-7b-instruct-v0.2.Q5_K_S.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| 7.50 GB | large, low quality loss - recommended |
122
+ | [mistral-7b-instruct-v0.2.Q5_K_M.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| 7.63 GB | large, very low quality loss - recommended |
123
+ | [mistral-7b-instruct-v0.2.Q6_K.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q6_K.gguf) | Q6_K | 6 | 5.94 GB| 8.44 GB | very large, extremely low quality loss |
124
+ | [mistral-7b-instruct-v0.2.Q8_0.gguf](https://huggingface.co/TheBlock/Mistral-7B-Instruct-v0.2-GGUF/blob/main/mistral-7b-instruct-v0.2.Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| 10.20 GB | very large, extremely low quality loss - not recommended |
125
 
126
  **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
127
 
 
142
 
143
  ### In `text-generation-webui`
144
 
145
+ Under Download Model, you can enter the model repo: TheBlock/Mistral-7B-Instruct-v0.2-GGUF and below it, a specific filename to download, such as: mistral-7b-instruct-v0.2.Q4_K_M.gguf.
146
 
147
  Then click Download.
148
 
 
157
  Then you can download any individual model file to the current directory, at high speed, with a command like this:
158
 
159
  ```shell
160
+ huggingface-cli download TheBlock/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
161
  ```
162
 
163
  <details>
 
166
  You can also download multiple files at once with a pattern:
167
 
168
  ```shell
169
+ huggingface-cli download TheBlock/Mistral-7B-Instruct-v0.2-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
170
  ```
171
 
172
  For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
 
180
  And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
181
 
182
  ```shell
183
+ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBlock/Mistral-7B-Instruct-v0.2-GGUF mistral-7b-instruct-v0.2.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
184
  ```
185
 
186
  Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
 
289
 
290
  For further support, and discussions on these models and AI in general, join us at:
291
 
292
+ [TheBlock AI's Discord server](https://discord.gg/TheBlokeai)
293
 
294
  ## Thanks, and how to contribute
295