Text Generation
Transformers
Safetensors
qwen3
unsloth
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use MusYW/raft_rag2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MusYW/raft_rag2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MusYW/raft_rag2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MusYW/raft_rag2") model = AutoModelForCausalLM.from_pretrained("MusYW/raft_rag2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MusYW/raft_rag2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MusYW/raft_rag2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MusYW/raft_rag2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MusYW/raft_rag2
- SGLang
How to use MusYW/raft_rag2 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 "MusYW/raft_rag2" \ --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": "MusYW/raft_rag2", "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 "MusYW/raft_rag2" \ --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": "MusYW/raft_rag2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Desktop
- Docker Model Runner
How to use MusYW/raft_rag2 with Docker Model Runner:
docker model run hf.co/MusYW/raft_rag2
Training in progress, step 3
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -24,13 +24,13 @@
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"
|
| 28 |
"gate_proj",
|
| 29 |
-
"up_proj",
|
| 30 |
-
"o_proj",
|
| 31 |
"q_proj",
|
| 32 |
-
"
|
| 33 |
-
"
|
|
|
|
|
|
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
|
|
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
"gate_proj",
|
|
|
|
|
|
|
| 29 |
"q_proj",
|
| 30 |
+
"k_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"o_proj"
|
| 34 |
],
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40422168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24ba1496b5c998fccb71e2bf422115d3244b6d0f1b202a0d786fc891cb1680e8
|
| 3 |
size 40422168
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5713
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e34494304a071125d515c4437ac844d3782cca115c3bad3a4f44123ff6d33c49
|
| 3 |
size 5713
|