Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
unsloth
trl
sft
text-generation-inference
Instructions to use Ba2han/outputs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ba2han/outputs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Ba2han/outputs")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Ba2han/outputs") model = AutoModelForCausalLM.from_pretrained("Ba2han/outputs") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Ba2han/outputs with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Ba2han/outputs" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Ba2han/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Ba2han/outputs
- SGLang
How to use Ba2han/outputs 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 "Ba2han/outputs" \ --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": "Ba2han/outputs", "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 "Ba2han/outputs" \ --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": "Ba2han/outputs", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Unsloth Studio
How to use Ba2han/outputs with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/outputs to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Ba2han/outputs to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Ba2han/outputs to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Ba2han/outputs", max_seq_length=2048, ) - Docker Model Runner
How to use Ba2han/outputs with Docker Model Runner:
docker model run hf.co/Ba2han/outputs
Training in progress, step 400
Browse files- README.md +3 -3
- config.json +4 -4
- generation_config.json +2 -2
- model.safetensors +2 -2
- tokenizer.json +18 -0
- tokenizer_config.json +20 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,8 +3,8 @@ library_name: transformers
|
|
| 3 |
model_name: outputs
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
- unsloth
|
| 7 |
- sft
|
|
|
|
| 8 |
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
|
@@ -27,7 +27,7 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
@@ -37,7 +37,7 @@ This model was trained with SFT.
|
|
| 37 |
- TRL: 0.24.0
|
| 38 |
- Transformers: 5.5.0
|
| 39 |
- Pytorch: 2.10.0
|
| 40 |
-
- Datasets: 4.
|
| 41 |
- Tokenizers: 0.22.2
|
| 42 |
|
| 43 |
## Citations
|
|
|
|
| 3 |
model_name: outputs
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
- sft
|
| 7 |
+
- unsloth
|
| 8 |
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/gj7eichr)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
|
|
| 37 |
- TRL: 0.24.0
|
| 38 |
- Transformers: 5.5.0
|
| 39 |
- Pytorch: 2.10.0
|
| 40 |
+
- Datasets: 4.3.0
|
| 41 |
- Tokenizers: 0.22.2
|
| 42 |
|
| 43 |
## Citations
|
config.json
CHANGED
|
@@ -6,7 +6,7 @@
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 2,
|
| 8 |
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id":
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 1536,
|
|
@@ -56,7 +56,7 @@
|
|
| 56 |
],
|
| 57 |
"max_position_embeddings": 8192,
|
| 58 |
"max_window_layers": 40,
|
| 59 |
-
"model_name": "
|
| 60 |
"model_type": "qwen3",
|
| 61 |
"num_attention_heads": 16,
|
| 62 |
"num_hidden_layers": 40,
|
|
@@ -70,8 +70,8 @@
|
|
| 70 |
"sliding_window": null,
|
| 71 |
"tie_word_embeddings": true,
|
| 72 |
"transformers_version": "5.5.0",
|
| 73 |
-
"unsloth_version": "2026.7.
|
| 74 |
"use_cache": false,
|
| 75 |
"use_sliding_window": false,
|
| 76 |
-
"vocab_size":
|
| 77 |
}
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 2,
|
| 8 |
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 60800,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"hidden_size": 1536,
|
|
|
|
| 56 |
],
|
| 57 |
"max_position_embeddings": 8192,
|
| 58 |
"max_window_layers": 40,
|
| 59 |
+
"model_name": "checkpoint-5722",
|
| 60 |
"model_type": "qwen3",
|
| 61 |
"num_attention_heads": 16,
|
| 62 |
"num_hidden_layers": 40,
|
|
|
|
| 70 |
"sliding_window": null,
|
| 71 |
"tie_word_embeddings": true,
|
| 72 |
"transformers_version": "5.5.0",
|
| 73 |
+
"unsloth_version": "2026.7.2",
|
| 74 |
"use_cache": false,
|
| 75 |
"use_sliding_window": false,
|
| 76 |
+
"vocab_size": 60802
|
| 77 |
}
|
generation_config.json
CHANGED
|
@@ -2,12 +2,12 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"eos_token_id": [
|
| 5 |
-
|
| 6 |
],
|
| 7 |
"max_length": 8192,
|
| 8 |
"output_attentions": false,
|
| 9 |
"output_hidden_states": false,
|
| 10 |
"pad_token_id": 0,
|
| 11 |
"transformers_version": "5.5.0",
|
| 12 |
-
"use_cache":
|
| 13 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 2,
|
| 4 |
"eos_token_id": [
|
| 5 |
+
60800
|
| 6 |
],
|
| 7 |
"max_length": 8192,
|
| 8 |
"output_attentions": false,
|
| 9 |
"output_hidden_states": false,
|
| 10 |
"pad_token_id": 0,
|
| 11 |
"transformers_version": "5.5.0",
|
| 12 |
+
"use_cache": true
|
| 13 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0df04f618d1d05c113a38828a4c5ef6460336b9fc1d3cd4d44ac1a40916a3bcb
|
| 3 |
+
size 2641039512
|
tokenizer.json
CHANGED
|
@@ -2342,6 +2342,24 @@
|
|
| 2342 |
"rstrip": false,
|
| 2343 |
"normalized": false,
|
| 2344 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2345 |
}
|
| 2346 |
],
|
| 2347 |
"normalizer": {
|
|
|
|
| 2342 |
"rstrip": false,
|
| 2343 |
"normalized": false,
|
| 2344 |
"special": true
|
| 2345 |
+
},
|
| 2346 |
+
{
|
| 2347 |
+
"id": 60800,
|
| 2348 |
+
"content": "<|im_end|>",
|
| 2349 |
+
"single_word": false,
|
| 2350 |
+
"lstrip": false,
|
| 2351 |
+
"rstrip": false,
|
| 2352 |
+
"normalized": false,
|
| 2353 |
+
"special": true
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"id": 60801,
|
| 2357 |
+
"content": "<|im_start|>",
|
| 2358 |
+
"single_word": false,
|
| 2359 |
+
"lstrip": false,
|
| 2360 |
+
"rstrip": false,
|
| 2361 |
+
"normalized": false,
|
| 2362 |
+
"special": true
|
| 2363 |
}
|
| 2364 |
],
|
| 2365 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -2,7 +2,10 @@
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<bos>",
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
-
"eos_token": "<
|
|
|
|
|
|
|
|
|
|
| 6 |
"is_local": true,
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
"pad_token": "<pad>",
|
|
@@ -2089,6 +2092,22 @@
|
|
| 2089 |
"rstrip": false,
|
| 2090 |
"normalized": false,
|
| 2091 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2092 |
}
|
| 2093 |
}
|
| 2094 |
}
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
"bos_token": "<bos>",
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"<|im_start|>"
|
| 8 |
+
],
|
| 9 |
"is_local": true,
|
| 10 |
"model_max_length": 1000000000000000019884624838656,
|
| 11 |
"pad_token": "<pad>",
|
|
|
|
| 2092 |
"rstrip": false,
|
| 2093 |
"normalized": false,
|
| 2094 |
"special": true
|
| 2095 |
+
},
|
| 2096 |
+
"60800": {
|
| 2097 |
+
"content": "<|im_end|>",
|
| 2098 |
+
"single_word": false,
|
| 2099 |
+
"lstrip": false,
|
| 2100 |
+
"rstrip": false,
|
| 2101 |
+
"normalized": false,
|
| 2102 |
+
"special": true
|
| 2103 |
+
},
|
| 2104 |
+
"60801": {
|
| 2105 |
+
"content": "<|im_start|>",
|
| 2106 |
+
"single_word": false,
|
| 2107 |
+
"lstrip": false,
|
| 2108 |
+
"rstrip": false,
|
| 2109 |
+
"normalized": false,
|
| 2110 |
+
"special": true
|
| 2111 |
}
|
| 2112 |
}
|
| 2113 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5777
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fca29e5eb79657cbb9063a36f8a75cdba332e03ddfbba7316ce46ef48ffcbe6
|
| 3 |
size 5777
|