初始化项目，由ModelHub XC社区提供模型
Model: second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
||||
*.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
|
||||
FinGPT-MT-Llama-3-8B-LoR-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q6_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
FinGPT-MT-Llama-3-8B-LoRA-f16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q2_K.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b026b75cec79f75a02dea5f77836adec7cd6cff3869f9fa46dad760a6334136f
|
||||
size 3179131072
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_L.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:058c5327d2a55a52083997a53c4aebcb28cd0bb0742d5f148264c6910f8e12d6
|
||||
size 4321956032
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_M.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1c7400ef784a20fe5b45d44d7856d9df949cd0bcd9f3b4e7a5d3d23b179d571c
|
||||
size 4018917568
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_S.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:05842afa14e646fb54ccbb47011e534357cac0d32c05d5af59cf34500ff76080
|
||||
size 3664498880
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q4_0.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a2bee4e4d3fc6799a0dba23aaad502a1c713dc675f082541dca7471013c7527
|
||||
size 4661211328
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_M.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4bebb8b47fc9d113f01ab5113152074a806600017ea12040e547acce0a35922a
|
||||
size 4920733888
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_S.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c91f44d8e79d5ccc15c6b99c0ca05dc20d7b7869344c079a4a35477799c6d80
|
||||
size 4692668608
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q5_0.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q5_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:01cb997fad87d465f79c88343f283e99d5a3cb469177e1563a6dc2354288d098
|
||||
size 5599293632
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:888424ddf12ff63ae0600db334c41e120aafc725560661c25c9c27c714dbcb4f
|
||||
size 5732987072
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_S.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f5ef4752d496e8fb57e7cc9664bcd379a5a0b65af3305c20fba9ccd2b88ee3be
|
||||
size 5599293632
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q6_0.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q6_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c5cd60119a3b5880c4d78875f088ee7a4c9a0943f6a0facf1a523ca222fa0e97
|
||||
size 6596006080
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-Q8_0.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33bba7aa286a3f945f0378fb4fe6ec61eed97c6528cedf3c9e217911e2d6b5ea
|
||||
size 8540770496
|
||||
3
FinGPT-MT-Llama-3-8B-LoRA-f16.gguf
Normal file
3
FinGPT-MT-Llama-3-8B-LoRA-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:883ba2f0f9e3828b7b5342cebb57b95459f402875e652c548c8c0125346a4663
|
||||
size 16068890816
|
||||
97
README.md
Normal file
97
README.md
Normal file
@@ -0,0 +1,97 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
license: other
|
||||
license_name: llama3
|
||||
model_name: Llama3 8B
|
||||
arxiv: 2307.09288
|
||||
base_model: meta-llama/Meta-Llama-3-8B
|
||||
inference: false
|
||||
model_creator: Meta Llama3
|
||||
model_type: llama
|
||||
pipeline_tag: text-generation
|
||||
quantized_by: Second State Inc.
|
||||
---
|
||||
|
||||
<!-- 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 -->
|
||||
|
||||
# FinGPT-MT-Llama-3-8B-LoRA-GGUF
|
||||
|
||||
## Original Model
|
||||
|
||||
[meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
|
||||
|
||||
## LoRA Adapter
|
||||
|
||||
[FinGPT/fingpt-mt_llama3-8b_lora](https://huggingface.co/FinGPT/fingpt-mt_llama3-8b_lora)
|
||||
|
||||
## Run with LlamaEdge
|
||||
|
||||
- LlamaEdge version: coming soon
|
||||
|
||||
<!-- - LlamaEdge version: [v0.8.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.3) and above
|
||||
|
||||
- Prompt template
|
||||
|
||||
- Prompt type: `llama-3-chat`
|
||||
|
||||
- Prompt string
|
||||
|
||||
```text
|
||||
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||||
|
||||
{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
``` -->
|
||||
|
||||
- Context size: `8192`
|
||||
|
||||
<!-- - Run as LlamaEdge service
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf \
|
||||
llama-api-server.wasm \
|
||||
--prompt-template llama-3-chat \
|
||||
--ctx-size 8192 \
|
||||
--model-name Llama-3-8b
|
||||
```
|
||||
|
||||
- Run as LlamaEdge command app
|
||||
|
||||
```bash
|
||||
wasmedge --dir .:. --nn-preload default:GGML:AUTO:FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf \
|
||||
llama-chat.wasm \
|
||||
--prompt-template llama-3-chat \
|
||||
--ctx-size 8192 \
|
||||
``` -->
|
||||
|
||||
## Quantized GGUF Models
|
||||
|
||||
| Name | Quant method | Bits | Size | Use case |
|
||||
| ---- | ---- | ---- | ---- | ----- |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q2_K.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q3_K_L.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q3_K_M.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q3_K_S.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q4_0.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q4_K_M.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q4_K_S.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q5_0.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q5_K_S.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q6_K.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-Q8_0.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
|
||||
| [FinGPT-MT-Llama-3-8B-LoRA-f16.gguf](https://huggingface.co/second-state/FinGPT-MT-Llama-3-8B-LoRA-GGUF/blob/main/FinGPT-MT-Llama-3-8B-LoRA-f16.gguf) | f16 | 16 | 16.1 GB| |
|
||||
|
||||
*Quantized with llama.cpp b3807.*
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
Reference in New Issue
Block a user