初始化项目,由ModelHub XC社区提供模型
Model: smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF Source: Original Platform
This commit is contained in:
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
qwen2.5-coder-7b-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
158
README.md
Normal file
158
README.md
Normal file
@@ -0,0 +1,158 @@
|
|||||||
|
---
|
||||||
|
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/blob/main/LICENSE
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
tags:
|
||||||
|
- code
|
||||||
|
- codeqwen
|
||||||
|
- chat
|
||||||
|
- qwen
|
||||||
|
- qwen-coder
|
||||||
|
- llama-cpp
|
||||||
|
- gguf-my-repo
|
||||||
|
---
|
||||||
|
|
||||||
|
# smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF
|
||||||
|
This model was converted to GGUF format from [`Qwen/Qwen2.5-Coder-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
||||||
|
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) for more details on the model.
|
||||||
|
|
||||||
|
|
||||||
|
## Ollama Modelfile (draft/beta!)
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
# ollama create qwen2.5-coder-7b-instruct:q8_0 -f modelfiles/Modelfile-qwen2.5-coder
|
||||||
|
|
||||||
|
FROM ../qwen2.5-coder-7b-instruct-q8_0.gguf
|
||||||
|
|
||||||
|
# This is Sam's hacked up template 2024-09-19
|
||||||
|
TEMPLATE """
|
||||||
|
{{- $fim_prefix := .FIMPrefix -}}
|
||||||
|
{{- $fim_suffix := .FIMSuffix -}}
|
||||||
|
{{- $repo_name := .RepoName -}}
|
||||||
|
{{- $files := .Files -}}
|
||||||
|
{{- $has_tools := gt (len .Tools) 0 -}}
|
||||||
|
{{- if $fim_prefix -}}
|
||||||
|
<|fim_prefix|>{{ $fim_prefix }}<|fim_suffix|>{{ $fim_suffix }}<|fim_middle|>
|
||||||
|
{{- else if $repo_name -}}
|
||||||
|
<|repo_name|>{{ $repo_name }}
|
||||||
|
{{- range $files }}
|
||||||
|
<|file_sep|>{{ .Path }}
|
||||||
|
{{ .Content }}
|
||||||
|
{{- end }}
|
||||||
|
{{- else -}}
|
||||||
|
{{- if or .System $has_tools -}}
|
||||||
|
<|im_start|>system
|
||||||
|
{{- if .System }}
|
||||||
|
{{ .System }}
|
||||||
|
{{- end }}
|
||||||
|
{{- if $has_tools }}
|
||||||
|
|
||||||
|
# Tools
|
||||||
|
|
||||||
|
You may call one or more functions to assist with the user query.
|
||||||
|
|
||||||
|
You are provided with function signatures within <tools></tools> XML tags:
|
||||||
|
<tools>
|
||||||
|
{{- range .Tools }}
|
||||||
|
{"type": "function", "function": {{ .Function }}}
|
||||||
|
{{- end }}
|
||||||
|
</tools>
|
||||||
|
|
||||||
|
For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
|
||||||
|
<tool_call>
|
||||||
|
{"name": <function-name>, "arguments": <args-json-object>}
|
||||||
|
</tool_call>
|
||||||
|
{{- end }}
|
||||||
|
<|im_end|>
|
||||||
|
{{- end }}
|
||||||
|
{{- if .Messages }}
|
||||||
|
{{- range $i, $message := .Messages }}
|
||||||
|
{{- if eq .Role "user" }}<|im_start|>user
|
||||||
|
{{ .Content }}<|im_end|>
|
||||||
|
{{- else if eq .Role "assistant" }}<|im_start|>assistant
|
||||||
|
{{- if .Content }}{{ .Content }}
|
||||||
|
{{- else if .ToolCalls }}<tool_call>
|
||||||
|
{{- range .ToolCalls }}
|
||||||
|
{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}}
|
||||||
|
{{- end }}
|
||||||
|
</tool_call>
|
||||||
|
{{- end }}<|im_end|>
|
||||||
|
{{- else if eq .Role "tool" }}<|im_start|>user
|
||||||
|
<tool_response>
|
||||||
|
{{ .Content }}
|
||||||
|
</tool_response><|im_end|>
|
||||||
|
{{- end }}
|
||||||
|
{{- end }}
|
||||||
|
{{- else if .Prompt -}}
|
||||||
|
<|im_start|>user
|
||||||
|
{{ .Prompt }}<|im_end|>
|
||||||
|
{{- end -}}
|
||||||
|
<|im_start|>assistant
|
||||||
|
{{ .Response }}
|
||||||
|
{{- end -}}
|
||||||
|
"""
|
||||||
|
|
||||||
|
PARAMETER stop "<|im_start|>"
|
||||||
|
PARAMETER stop "<|im_end|>"
|
||||||
|
PARAMETER stop "<|fim_prefix|>"
|
||||||
|
PARAMETER stop "<|fim_suffix|>"
|
||||||
|
PARAMETER stop "<|fim_middle|>"
|
||||||
|
PARAMETER stop "<|repo_name|>"
|
||||||
|
PARAMETER stop "<|file_sep|>"
|
||||||
|
|
||||||
|
### Tuning ##
|
||||||
|
PARAMETER num_ctx 16384
|
||||||
|
PARAMETER temperature 0.3
|
||||||
|
PARAMETER top_p 0.8
|
||||||
|
|
||||||
|
# PARAMETER num_batch 1024
|
||||||
|
# PARAMETER num_keep 512
|
||||||
|
# PARAMETER presence_penalty 0.2
|
||||||
|
# PARAMETER frequency_penalty 0.2
|
||||||
|
# PARAMETER repeat_last_n 50
|
||||||
|
```
|
||||||
|
|
||||||
|
## Use with llama.cpp
|
||||||
|
Install llama.cpp through brew (works on Mac and Linux)
|
||||||
|
|
||||||
|
```bash
|
||||||
|
brew install llama.cpp
|
||||||
|
|
||||||
|
```
|
||||||
|
Invoke the llama.cpp server or the CLI.
|
||||||
|
|
||||||
|
### CLI:
|
||||||
|
```bash
|
||||||
|
llama-cli --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Server:
|
||||||
|
```bash
|
||||||
|
llama-server --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -c 2048
|
||||||
|
```
|
||||||
|
|
||||||
|
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.
|
||||||
|
|
||||||
|
Step 1: Clone llama.cpp from GitHub.
|
||||||
|
```
|
||||||
|
git clone https://github.com/ggerganov/llama.cpp
|
||||||
|
```
|
||||||
|
|
||||||
|
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).
|
||||||
|
```
|
||||||
|
cd llama.cpp && LLAMA_CURL=1 make
|
||||||
|
```
|
||||||
|
|
||||||
|
Step 3: Run inference through the main binary.
|
||||||
|
```
|
||||||
|
./llama-cli --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
|
||||||
|
```
|
||||||
|
or
|
||||||
|
```
|
||||||
|
./llama-server --hf-repo smcleod/Qwen2.5-Coder-7B-Instruct-Q8_0-GGUF --hf-file qwen2.5-coder-7b-instruct-q8_0.gguf -c 2048
|
||||||
|
```
|
||||||
3
qwen2.5-coder-7b-instruct-q8_0.gguf
Normal file
3
qwen2.5-coder-7b-instruct-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:8dc646852b6cf37ca45fbf5232f0ccf5ad9cea1d30348cc373fdf21fa04cd5e1
|
||||||
|
size 8098525696
|
||||||
Reference in New Issue
Block a user