snakeying commited on
Commit
06cda31
·
verified ·
1 Parent(s): 1a920aa

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -60
README.md CHANGED
@@ -1,60 +1,22 @@
1
- ---
2
- base_model: THUDM/LongWriter-llama3.1-8b
3
- datasets:
4
- - THUDM/LongWriter-6k
5
- language:
6
- - en
7
- - zh
8
- library_name: transformers
9
- license: llama3.1
10
- tags:
11
- - Long Context
12
- - chatglm
13
- - llama
14
- - llama-cpp
15
- - gguf-my-repo
16
- ---
17
-
18
- # snakeying/LongWriter-llama3.1-8b-Q8_0-GGUF
19
- This model was converted to GGUF format from [`THUDM/LongWriter-llama3.1-8b`](https://huggingface.co/THUDM/LongWriter-llama3.1-8b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
20
- Refer to the [original model card](https://huggingface.co/THUDM/LongWriter-llama3.1-8b) for more details on the model.
21
-
22
- ## Use with llama.cpp
23
- Install llama.cpp through brew (works on Mac and Linux)
24
-
25
- ```bash
26
- brew install llama.cpp
27
-
28
- ```
29
- Invoke the llama.cpp server or the CLI.
30
-
31
- ### CLI:
32
- ```bash
33
- llama-cli --hf-repo snakeying/LongWriter-llama3.1-8b-Q8_0-GGUF --hf-file longwriter-llama3.1-8b-q8_0.gguf -p "The meaning to life and the universe is"
34
- ```
35
-
36
- ### Server:
37
- ```bash
38
- llama-server --hf-repo snakeying/LongWriter-llama3.1-8b-Q8_0-GGUF --hf-file longwriter-llama3.1-8b-q8_0.gguf -c 2048
39
- ```
40
-
41
- Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
42
-
43
- Step 1: Clone llama.cpp from GitHub.
44
- ```
45
- git clone https://github.com/ggerganov/llama.cpp
46
- ```
47
-
48
- Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
49
- ```
50
- cd llama.cpp && LLAMA_CURL=1 make
51
- ```
52
-
53
- Step 3: Run inference through the main binary.
54
- ```
55
- ./llama-cli --hf-repo snakeying/LongWriter-llama3.1-8b-Q8_0-GGUF --hf-file longwriter-llama3.1-8b-q8_0.gguf -p "The meaning to life and the universe is"
56
- ```
57
- or
58
- ```
59
- ./llama-server --hf-repo snakeying/LongWriter-llama3.1-8b-Q8_0-GGUF --hf-file longwriter-llama3.1-8b-q8_0.gguf -c 2048
60
- ```
 
1
+ TEMPLATE for Ollama Modelfile
2
+
3
+ TEMPLATE """
4
+ {{- range $i, $_ := .Messages }}
5
+ {{- if eq .Role "user" }}
6
+ {{- if and $.Tools (le (len (slice $.Messages $i)) 2) }}[AVAILABLE_TOOLS] {{ $.Tools }}[/AVAILABLE_TOOLS]
7
+ {{- end }}[INST] {{ if and $.System (eq (len (slice $.Messages $i)) 1) }}{{ $.System }}
8
+
9
+ {{ end }}{{ .Content }}[/INST]
10
+ {{- else if eq .Role "assistant" }}
11
+ {{- if .Content }} {{ .Content }}{{ if not (eq (len (slice $.Messages $i)) 1) }}</s>{{ end }}
12
+ {{- else if .ToolCalls }}[TOOL_CALLS] [
13
+ {{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
14
+ {{- end }}]</s>
15
+ {{- end }}
16
+ {{- else if eq .Role "tool" }}[TOOL_RESULTS] {"content": {{ .Content }}} [/TOOL_RESULTS]
17
+ {{- end }}
18
+ {{- end }}
19
+ """
20
+
21
+ PARAMETER stop "[INST]"
22
+ PARAMETER stop "[/INST]"