初始化项目，由ModelHub XC社区提供模型
Model: second-state/Qwen2-7B-Instruct-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
48
.gitattributes
vendored
Normal file
48
.gitattributes
vendored
Normal file
@@ -0,0 +1,48 @@
|
||||
*.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
|
||||
Qwen2-7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Qwen2-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Qwen2-7B-Instruct-Q2_K.gguf
Normal file
3
Qwen2-7B-Instruct-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:848963f9fc73581a55722ec7df655f9e1b0cd3ec4d3e3285309d222ac7fddf16
|
||||
size 3015937568
|
||||
3
Qwen2-7B-Instruct-Q3_K_L.gguf
Normal file
3
Qwen2-7B-Instruct-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bec871859dfb3b162b4a8dd942a01d3249cc238a0766615c74862826495e1f41
|
||||
size 4088456736
|
||||
3
Qwen2-7B-Instruct-Q3_K_M.gguf
Normal file
3
Qwen2-7B-Instruct-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57496563e116df4f86a1fec21e46f5b05ee649a8d00b7942f82540abcb5697a4
|
||||
size 3808388640
|
||||
3
Qwen2-7B-Instruct-Q3_K_S.gguf
Normal file
3
Qwen2-7B-Instruct-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0095bd5776b379ad84e14768205bd5626d1414021660a9ca146b7956677dab3a
|
||||
size 3492365856
|
||||
3
Qwen2-7B-Instruct-Q4_0.gguf
Normal file
3
Qwen2-7B-Instruct-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:97d64ebb159ff2940801c0e3be85ce0f62c49c7fdc7b6e4d4bbd01dff1624792
|
||||
size 4431388192
|
||||
3
Qwen2-7B-Instruct-Q4_K_M.gguf
Normal file
3
Qwen2-7B-Instruct-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:143bc13bb99079bba3b47c3e4309cd143dbf020f558acb606906d4d4e8ff7ac6
|
||||
size 4683071008
|
||||
3
Qwen2-7B-Instruct-Q4_K_S.gguf
Normal file
3
Qwen2-7B-Instruct-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:335dc196141077df3c2b366cdc030dc9eb3fb56a8715dbd2ab0f6bfbee436711
|
||||
size 4457766432
|
||||
3
Qwen2-7B-Instruct-Q5_0.gguf
Normal file
3
Qwen2-7B-Instruct-Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78a590030cfd708f4d572c6a217d62b7aaa8b06b755465e5aea429d04297ffc0
|
||||
size 5315173920
|
||||
3
Qwen2-7B-Instruct-Q5_K_M.gguf
Normal file
3
Qwen2-7B-Instruct-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd190a5a43c597ac946b6595351ea4410ccb43462856e608c553ca3f0889c88d
|
||||
size 5444828704
|
||||
3
Qwen2-7B-Instruct-Q5_K_S.gguf
Normal file
3
Qwen2-7B-Instruct-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:87154b1089727deb7d1952c58e3039c3245e250603c0bce751946ccc4334b8e6
|
||||
size 5315173920
|
||||
3
Qwen2-7B-Instruct-Q6_K.gguf
Normal file
3
Qwen2-7B-Instruct-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:babb35399ae032173c01aee36f46246aaa114730374bf3fecaa435ea7eef6cd0
|
||||
size 6254196256
|
||||
3
Qwen2-7B-Instruct-Q8_0.gguf
Normal file
3
Qwen2-7B-Instruct-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c3c7010ad6ed817799645fc4d83cf607132311677fe53408bd812dcdeb1311f
|
||||
size 8098522656
|
||||
3
Qwen2-7B-Instruct-f16.gguf
Normal file
3
Qwen2-7B-Instruct-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2640a828a839956454e9904b5811c8b7cfd3a1323312e3bf3bcc05a978fa38e5
|
||||
size 15237850656
|
||||
85
README.md
Normal file
85
README.md
Normal file
@@ -0,0 +1,85 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2-7B-Instruct
|
||||
license: apache-2.0
|
||||
model_creator: Qwen
|
||||
model_name: Qwen2-7B-Instruct
|
||||
quantized_by: Second State Inc.
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- chat
|
||||
---
|
||||
|
||||
<!-- header start -->
|
||||
<!-- 200823 -->
|
||||
<div style="width: auto; margin-left: auto; margin-right: auto">
|
||||
<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
||||
</div>
|
||||
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
||||
<!-- header end -->
|
||||
|
||||
# Qwen2-7B-Instruct-GGUF
|
||||
|
||||
## Original Model
|
||||
|
||||
[Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)
|
||||
|
||||
## Run with LlamaEdge
|
||||
|
||||
- LlamaEdge version: [v0.11.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.11.2)
|
||||
|
||||
- Prompt template
|
||||
|
||||
- Prompt type: `chatml`
|
||||
|
||||
- Prompt string
|
||||
|
||||
```text
|
||||
<|im_start|>system
|
||||
{system_message}<|im_end|>
|
||||
<|im_start|>user
|
||||
{prompt}<|im_end|>
|
||||
<|im_start|>assistant
|
||||
```
|
||||
|
||||
- Context size: `131072`
|
||||
|
||||
- Run as LlamaEdge service
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-7B-Instruct-Q5_K_M.gguf \
|
||||
llama-api-server.wasm \
|
||||
--model-name Qwen2-7B-Instruct \
|
||||
--prompt-template chatml \
|
||||
--ctx-size 131072
|
||||
```
|
||||
|
||||
- Run as LlamaEdge command app
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2-7B-Instruct-Q5_K_M.gguf \
|
||||
llama-chat.wasm \
|
||||
--prompt-template chatml \
|
||||
--ctx-size 131072
|
||||
```
|
||||
|
||||
## Quantized GGUF Models
|
||||
|
||||
| Name | Quant method | Bits | Size | Use case |
|
||||
| ---- | ---- | ---- | ---- | ----- |
|
||||
| [Qwen2-7B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.02 GB| smallest, significant quality loss - not recommended for most purposes |
|
||||
| [Qwen2-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.09 GB| small, substantial quality loss |
|
||||
| [Qwen2-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss |
|
||||
| [Qwen2-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.49 GB| very small, high quality loss |
|
||||
| [Qwen2-7B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
||||
| [Qwen2-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.68 GB| medium, balanced quality - recommended |
|
||||
| [Qwen2-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.46 GB| small, greater quality loss |
|
||||
| [Qwen2-7B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.32 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
||||
| [Qwen2-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.44 GB| large, very low quality loss - recommended |
|
||||
| [Qwen2-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.32 GB| large, low quality loss - recommended |
|
||||
| [Qwen2-7B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.25 GB| very large, extremely low quality loss |
|
||||
| [Qwen2-7B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.21 GB| very large, extremely low quality loss - not recommended |
|
||||
| [Qwen2-7B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-f16.gguf) | f16 | 16 | 15.2 GB| |
|
||||
|
||||
*Quantized with llama.cpp b3705*
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.41.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework":"other","task":"text-generation"}
|
||||
Reference in New Issue
Block a user