Instructions to use v2ray/GPT4chan-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use v2ray/GPT4chan-24B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="v2ray/GPT4chan-24B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("v2ray/GPT4chan-24B") model = AutoModelForCausalLM.from_pretrained("v2ray/GPT4chan-24B") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use v2ray/GPT4chan-24B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "v2ray/GPT4chan-24B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "v2ray/GPT4chan-24B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/v2ray/GPT4chan-24B
- SGLang
How to use v2ray/GPT4chan-24B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "v2ray/GPT4chan-24B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "v2ray/GPT4chan-24B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "v2ray/GPT4chan-24B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "v2ray/GPT4chan-24B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use v2ray/GPT4chan-24B with Docker Model Runner:
docker model run hf.co/v2ray/GPT4chan-24B
Uploaded better trained version.
Browse files
README.md
CHANGED
|
@@ -10,9 +10,11 @@ pipeline_tag: text-generation
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
# GPT4chan 24B
|
|
|
|
|
|
|
| 13 |
This model is [mistralai/Mistral-Small-24B-Base-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501) merged with [v2ray/GPT4chan-24B-QLoRA](https://huggingface.co/v2ray/GPT4chan-24B-QLoRA).
|
| 14 |
|
| 15 |
-
Trained using 8x H100 with global batch size 64, using 2e-4 learning rate, for
|
| 16 |
## Prompt Format
|
| 17 |
```
|
| 18 |
board<|start_header_id|>id<|end_header_id|>content<|start_header_id|>id<|end_header_id|>content...<|start_header_id|>id<|end_header_id|>
|
|
|
|
| 10 |
library_name: transformers
|
| 11 |
---
|
| 12 |
# GPT4chan 24B
|
| 13 |
+

|
| 14 |
+
|
| 15 |
This model is [mistralai/Mistral-Small-24B-Base-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Base-2501) merged with [v2ray/GPT4chan-24B-QLoRA](https://huggingface.co/v2ray/GPT4chan-24B-QLoRA).
|
| 16 |
|
| 17 |
+
Trained using 8x H100 with global batch size 64, using 2e-4 learning rate, for 4000 steps, which is approximately 5 epochs.
|
| 18 |
## Prompt Format
|
| 19 |
```
|
| 20 |
board<|start_header_id|>id<|end_header_id|>content<|start_header_id|>id<|end_header_id|>content...<|start_header_id|>id<|end_header_id|>
|
model-00001-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9898729408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41cd0718baa0ae975171e5b50ad14a8ca4ffaeb1e59d4c882a9d56dcc953ee4b
|
| 3 |
size 9898729408
|
model-00002-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9668064384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2ee0bfa89960973d0847f66143a758f242876312b844f9d047f67c92c774650
|
| 3 |
size 9668064384
|
model-00003-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9668064400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01308b5bb3f5f86f97dd3e67388d86197b2fc31561a9da6cfa42a346fa036657
|
| 3 |
size 9668064400
|
model-00004-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 9961665680
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:477879690661c77bfb25cac5f024ff30c27d274cc087b45ca0f22ef8aa9d0cd9
|
| 3 |
size 9961665680
|
model-00005-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7948365856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:348f10663354eda68d077984ee70059172ee7c675e5799ed923fc47b2c15763d
|
| 3 |
size 7948365856
|