Text Generation
Transformers
Safetensors
qwen3
cooking
recipes
dpo
provenance
abstention
conversational
text-generation-inference
Instructions to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant") model = AutoModelForCausalLM.from_pretrained("HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant
- SGLang
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant 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 "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant with Docker Model Runner:
docker model run hf.co/HumanjavaEnterprises/Qwen3-8B-Cooking-Assistant
Card corrections 2026-11-14 (21 eval languages, no training counts, transformers 5 example); tokenizer_config: drop local loader flags
Browse files- README.md +8 -5
- tokenizer_config.json +0 -2
README.md
CHANGED
|
@@ -14,7 +14,7 @@ datasets: [HumanjavaEnterprises/cooking-assistant-eval]
|
|
| 14 |
A cooking assistant that reads the recipe you give it, and asks for the recipe instead of inventing details when it
|
| 15 |
can't see one. On questions that need a recipe it wasn't shown, it invents details 2.7% of the time vs 25.8% for base
|
| 16 |
Qwen3-8B; given the recipe, it answers correctly 94.8% of the time vs 83.1% (four open judges, 3 of 4 agreeing). General
|
| 17 |
-
cooking answers are level with the base. 26 languages; runs on a 6 GB GPU (Q4_K_M).
|
| 18 |
|
| 19 |
*Unofficial fine-tune of Qwen3-8B by Humanjava Enterprises; not made or endorsed by Alibaba Cloud or the Qwen team.*
|
| 20 |
|
|
@@ -47,8 +47,9 @@ tok = AutoTokenizer.from_pretrained(repo)
|
|
| 47 |
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")
|
| 48 |
messages = [{"role": "system", "content": "You are a cooking assistant. You answer questions about dishes, ingredients, techniques and food safety. When you are not sure, you say so."},
|
| 49 |
{"role": "user", "content": "If I double the recipe, how much pepper do I need?"}]
|
| 50 |
-
|
| 51 |
-
|
|
|
|
| 52 |
```
|
| 53 |
|
| 54 |
## Versions
|
|
@@ -60,6 +61,8 @@ The model is one product with dated versions. Each version is a git tag on this
|
|
| 60 |
|---|---|---|---|---|
|
| 61 |
| **v1** (current) | 2026-11-12 | 2.7% (base 25.8%) | 94.8% (base 83.1%) | first public release |
|
| 62 |
|
|
|
|
|
|
|
| 63 |
## Prompt format
|
| 64 |
|
| 65 |
Qwen3 chat template, **thinking off** (`enable_thinking: false`, or `/no_think` in the user turn). Trained with this
|
|
@@ -88,7 +91,7 @@ only, every training record traceable to its source, and the checks published al
|
|
| 88 |
|
| 89 |
## Results
|
| 90 |
|
| 91 |
-
All cooking scores are on a fixed held-out set of 682 questions in
|
| 92 |
recipe shown, 10 recall questions with no recipe ("how do you make X?"), 300 that need a recipe the model is not shown,
|
| 93 |
and 82 general questions. Answers from base Qwen3-8B
|
| 94 |
(thinking off) and this model are compared by an open-weights judge from a different model family
|
|
@@ -205,7 +208,7 @@ and per-row source credits) is published so the results can be checked:
|
|
| 205 |
answers at [label-test.humanjava.com](https://label-test.humanjava.com/?s=cook4&k=cook-9ac741a1e387&src=hf-card) (no account; we keep only a name or initials and your labels).
|
| 206 |
- Still invents on some no-recipe questions: about 1 in 40 when three of four judges must agree, about 1 in 16 by the
|
| 207 |
strictest single judge. Most remaining cases are borderline hedges (a common default offered with a caveat).
|
| 208 |
-
- Strongest in English and Spanish; Thai, Tamil and Hindi
|
| 209 |
- The old public-domain cookbooks reflect their era: measures, techniques, some outdated advice.
|
| 210 |
|
| 211 |
## Feedback and security
|
|
|
|
| 14 |
A cooking assistant that reads the recipe you give it, and asks for the recipe instead of inventing details when it
|
| 15 |
can't see one. On questions that need a recipe it wasn't shown, it invents details 2.7% of the time vs 25.8% for base
|
| 16 |
Qwen3-8B; given the recipe, it answers correctly 94.8% of the time vs 83.1% (four open judges, 3 of 4 agreeing). General
|
| 17 |
+
cooking answers are level with the base. Trained on 26 languages, evaluated in 21; runs on a 6 GB GPU (Q4_K_M).
|
| 18 |
|
| 19 |
*Unofficial fine-tune of Qwen3-8B by Humanjava Enterprises; not made or endorsed by Alibaba Cloud or the Qwen team.*
|
| 20 |
|
|
|
|
| 47 |
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")
|
| 48 |
messages = [{"role": "system", "content": "You are a cooking assistant. You answer questions about dishes, ingredients, techniques and food safety. When you are not sure, you say so."},
|
| 49 |
{"role": "user", "content": "If I double the recipe, how much pepper do I need?"}]
|
| 50 |
+
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, enable_thinking=False, return_dict=True, return_tensors="pt").to(model.device)
|
| 51 |
+
out = model.generate(**inputs, max_new_tokens=400)
|
| 52 |
+
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
|
| 53 |
```
|
| 54 |
|
| 55 |
## Versions
|
|
|
|
| 61 |
|---|---|---|---|---|
|
| 62 |
| **v1** (current) | 2026-11-12 | 2.7% (base 25.8%) | 94.8% (base 83.1%) | first public release |
|
| 63 |
|
| 64 |
+
**Corrections (2026-11-14):** the evaluation set covers 21 languages (this card said 26; the model was trained on 26); training counts removed from this card; Transformers example updated for transformers 5. No score changed.
|
| 65 |
+
|
| 66 |
## Prompt format
|
| 67 |
|
| 68 |
Qwen3 chat template, **thinking off** (`enable_thinking: false`, or `/no_think` in the user turn). Trained with this
|
|
|
|
| 91 |
|
| 92 |
## Results
|
| 93 |
|
| 94 |
+
All cooking scores are on a fixed held-out set of 682 questions in 21 languages, never used in training: 290 with the
|
| 95 |
recipe shown, 10 recall questions with no recipe ("how do you make X?"), 300 that need a recipe the model is not shown,
|
| 96 |
and 82 general questions. Answers from base Qwen3-8B
|
| 97 |
(thinking off) and this model are compared by an open-weights judge from a different model family
|
|
|
|
| 208 |
answers at [label-test.humanjava.com](https://label-test.humanjava.com/?s=cook4&k=cook-9ac741a1e387&src=hf-card) (no account; we keep only a name or initials and your labels).
|
| 209 |
- Still invents on some no-recipe questions: about 1 in 40 when three of four judges must agree, about 1 in 16 by the
|
| 210 |
strictest single judge. Most remaining cases are borderline hedges (a common default offered with a caveat).
|
| 211 |
+
- Strongest in English and Spanish, where most of the source texts are; languages with few source texts (such as Thai, Tamil and Hindi) are likely weaker.
|
| 212 |
- The old public-domain cookbooks reflect their era: measures, techniques, some outdated advice.
|
| 213 |
|
| 214 |
## Feedback and security
|
tokenizer_config.json
CHANGED
|
@@ -20,8 +20,6 @@
|
|
| 20 |
"<|image_pad|>",
|
| 21 |
"<|video_pad|>"
|
| 22 |
],
|
| 23 |
-
"is_local": true,
|
| 24 |
-
"local_files_only": true,
|
| 25 |
"model_max_length": 131072,
|
| 26 |
"pad_token": "<|endoftext|>",
|
| 27 |
"split_special_tokens": false,
|
|
|
|
| 20 |
"<|image_pad|>",
|
| 21 |
"<|video_pad|>"
|
| 22 |
],
|
|
|
|
|
|
|
| 23 |
"model_max_length": 131072,
|
| 24 |
"pad_token": "<|endoftext|>",
|
| 25 |
"split_special_tokens": false,
|