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: recipe-shown correctness reported apart (94.8% vs 83.1%), quant rows corrected
Browse files
README.md
CHANGED
|
@@ -98,6 +98,13 @@ applied to all four, the share of no-recipe answers that invent recipe details:
|
|
| 98 |
| all four say so | 19.1% | 1.0% |
|
| 99 |
| any one says so | 49.2% | 18.3% |
|
| 100 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
Every judge, and every way of combining them, shows a significant drop (3 of 4: 72 questions where only the base
|
| 102 |
invents, 3 where only this model does, McNemar p < 1e-17). The judges agree moderately on base answers (Fleiss kappa
|
| 103 |
0.63). GLM-4.7-Flash flags more of this model's answers than the others; reading them, most repeat or restate a line
|
|
@@ -114,10 +121,10 @@ itself, or a common default ("a pinch of salt") offered with a hedge.
|
|
| 114 |
| Correct when the recipe is shown | 94.0% | 93.3% | 93.7% |
|
| 115 |
| Invents with no recipe (full precision on that run) | 9.3% (7.3%) | 6.3% (6.3%) | 6.7% (6.7%) |
|
| 116 |
| Invents with no recipe, 3 of 4 judges (full precision) | 4.7% (3.3%) | 3.0% (3.3%) | 3.3% (2.7%) |
|
| 117 |
-
| Correct when the recipe is shown, 3 of 4 judges (full precision) |
|
| 118 |
|
| 119 |
With all four judges, no quantised file differs significantly from full precision (McNemar on the 3-of-4 verdict:
|
| 120 |
-
Q4_K_M p = 0.34, Q6_K p = 1.0, Q8_0 p = 0.69 for inventing). On Q4_K_M two of the four judges on their own
|
| 121 |
(GLM-4.7-Flash, gpt-oss-120b) do see slightly more invented details (p = 0.02 and 0.04); pick Q6_K or Q8_0 if that matters.
|
| 122 |
|
| 123 |
No quantisation changes the invents rate significantly (McNemar p ≥ 0.29). Q8_0's small dip comes from the 82
|
|
|
|
| 98 |
| all four say so | 19.1% | 1.0% |
|
| 99 |
| any one says so | 49.2% | 18.3% |
|
| 100 |
|
| 101 |
+
The same four judges on the questions where the recipe **is** shown and the model has to read it (290 questions; 3 of
|
| 102 |
+
4 must agree): Qwen3-8B correct 83.1% [78.4, 87.0], this model **94.8%** [91.6, 96.8] (40 questions only this model
|
| 103 |
+
gets right, 6 only the base does, McNemar p < 1e-6). Two other kinds of question in the set are reported apart:
|
| 104 |
+
82 general questions graded against a reference answer (40.2% for both models; the judges disagree widely there) and
|
| 105 |
+
10 "how do you make X?" questions with no recipe whose reference is the original 1800s text (0% for both: the model
|
| 106 |
+
is built not to recall historical recipes from memory).
|
| 107 |
+
|
| 108 |
Every judge, and every way of combining them, shows a significant drop (3 of 4: 72 questions where only the base
|
| 109 |
invents, 3 where only this model does, McNemar p < 1e-17). The judges agree moderately on base answers (Fleiss kappa
|
| 110 |
0.63). GLM-4.7-Flash flags more of this model's answers than the others; reading them, most repeat or restate a line
|
|
|
|
| 121 |
| Correct when the recipe is shown | 94.0% | 93.3% | 93.7% |
|
| 122 |
| Invents with no recipe (full precision on that run) | 9.3% (7.3%) | 6.3% (6.3%) | 6.7% (6.7%) |
|
| 123 |
| Invents with no recipe, 3 of 4 judges (full precision) | 4.7% (3.3%) | 3.0% (3.3%) | 3.3% (2.7%) |
|
| 124 |
+
| Correct when the recipe is shown, 3 of 4 judges (full precision) | 95.5% (94.1%) | 95.5% (94.1%) | 95.2% (94.8%) |
|
| 125 |
|
| 126 |
With all four judges, no quantised file differs significantly from full precision (McNemar on the 3-of-4 verdict:
|
| 127 |
+
Q4_K_M p = 0.34, Q6_K p = 1.0, Q8_0 p = 0.69 for inventing; p ≥ 0.22 for correctness with the recipe shown). On Q4_K_M two of the four judges on their own
|
| 128 |
(GLM-4.7-Flash, gpt-oss-120b) do see slightly more invented details (p = 0.02 and 0.04); pick Q6_K or Q8_0 if that matters.
|
| 129 |
|
| 130 |
No quantisation changes the invents rate significantly (McNemar p ≥ 0.29). Q8_0's small dip comes from the 82
|