MaziyarPanahi commited on
Commit
32069f8
1 Parent(s): e317e9d

Update README.md (#2)

Browse files

- Update README.md (ec73cdd4bbdf3c6413a2312fdc26908600cd8e30)

Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -98,7 +98,7 @@ pip3 install huggingface-hub
98
  Then you can download any individual model file to the current directory, at high speed, with a command like this:
99
 
100
  ```shell
101
- huggingface-cli download MaziyarPanahi/Hermes-2-Pro-11B-GGUF Hermes-2-Pro-11B-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
102
  ```
103
  </details>
104
  <details>
@@ -121,7 +121,7 @@ pip3 install hf_transfer
121
  And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
122
 
123
  ```shell
124
- HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/Hermes-2-Pro-11B-GGUF Hermes-2-Pro-11B-GGUF.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
125
  ```
126
 
127
  Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
@@ -132,7 +132,7 @@ Windows Command Line users: You can set the environment variable by running `set
132
  Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
133
 
134
  ```shell
135
- ./main -ngl 35 -m Hermes-2-Pro-11B-GGUF.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
136
  {system_message}<|im_end|>
137
  <|im_start|>user
138
  {prompt}<|im_end|>
@@ -209,7 +209,7 @@ output = llm(
209
 
210
  # Chat Completion API
211
 
212
- llm = Llama(model_path="./Hermes-2-Pro-11B-GGUF.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
213
  llm.create_chat_completion(
214
  messages = [
215
  {"role": "system", "content": "You are a story writing assistant."},
 
98
  Then you can download any individual model file to the current directory, at high speed, with a command like this:
99
 
100
  ```shell
101
+ huggingface-cli download MaziyarPanahi/Hermes-2-Pro-11B-GGUF Hermes-2-Pro-11B.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
102
  ```
103
  </details>
104
  <details>
 
121
  And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
122
 
123
  ```shell
124
+ HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MaziyarPanahi/Hermes-2-Pro-11B-GGUF Hermes-2-Pro-11B.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
125
  ```
126
 
127
  Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
 
132
  Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
133
 
134
  ```shell
135
+ ./main -ngl 35 -m Hermes-2-Pro-11B.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system
136
  {system_message}<|im_end|>
137
  <|im_start|>user
138
  {prompt}<|im_end|>
 
209
 
210
  # Chat Completion API
211
 
212
+ llm = Llama(model_path="./Hermes-2-Pro-11B.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
213
  llm.create_chat_completion(
214
  messages = [
215
  {"role": "system", "content": "You are a story writing assistant."},