Instructions to use hi1hello/FriendliAI-broken-model-fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hi1hello/FriendliAI-broken-model-fixed with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hi1hello/FriendliAI-broken-model-fixed")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hi1hello/FriendliAI-broken-model-fixed")
model = AutoModelForCausalLM.from_pretrained("hi1hello/FriendliAI-broken-model-fixed", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hi1hello/FriendliAI-broken-model-fixed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hi1hello/FriendliAI-broken-model-fixed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hi1hello/FriendliAI-broken-model-fixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hi1hello/FriendliAI-broken-model-fixed

SGLang

How to use hi1hello/FriendliAI-broken-model-fixed 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 "hi1hello/FriendliAI-broken-model-fixed" \
    --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": "hi1hello/FriendliAI-broken-model-fixed",
		"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 "hi1hello/FriendliAI-broken-model-fixed" \
        --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": "hi1hello/FriendliAI-broken-model-fixed",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hi1hello/FriendliAI-broken-model-fixed with Docker Model Runner:
```
docker model run hf.co/hi1hello/FriendliAI-broken-model-fixed
```

Changes Q1-a

1. Added 'chat_template to 'tokenizer-config.json'

Problem: The original 'tokenizer_config.json' was missing the 'chat_template' field.
Impact: Without a chat template, werving frameworks cannot convert(vLLM, TGI, SGLang).
Fix: Added the standard Qwen3 chat template from the official 'Qwen/Qwen3-8B' repository.

2. Corrected 'base model' in 'README.md'

Problem: 'base_model' was set to 'meta-llama/Meta-Llama-3.18B'.
Evidence:
- 'config.json' specifies '"model_type": "qwen3" and '"architectures": ["Qwen3ForCausalLM"]'
- 'vocab_size' is 151936(Qwen3), not 128256(Llama-3.1)
- 'num_hidden_layers' is 36(Qwen3-8B), not 32(Llama-3.1)
- 'intermediate_size' is 12288(Qwen3-8B), not 14336(Llama-3.1-8B)
- Tokenizer uses Qwen-specific special tokens('<|im_start|>', <|im_end|>, etc)
- Total weight size(16.4GB) matches official Qwen3-8B
Fix: Changed 'base_model' to 'Qwen/Qwen3-8B'

Changes Q1-b

Why 'reasoning_effort' has no effect

The 'reasoning_effort' parameter is designed to control how much "thinking" a model does before responding. However, this Qwen3-8B model only supports a binary toggle ('enable_thinking=True/False') via its chat template, not a continuous effort scale.

The 'reasoning_effort' parameter is an API-level concept that requires explicit support in both the serving engine and the model. Qwen3-8B was not trained to modulate reasoning depth based on an effort parameter — it either thinks (generates ... blocks) or it doesn't.

Requirements to make it functional

Serving Engine Support: The inference API must parse the 'reasoning_effort' parameter and translate it into actionable behavior. Currently, most engines pass it through without interpretation for Qwen3 models.
Mapping to existing mechanisms: The engine could map 'reasoning_effort' to Qwen3's existing controls:
- 'low' → 'enable_thinking=False'
- 'medium' → 'enable_thinking=True' + limit thinking tokens
- 'high' → 'enable_thinking=True' + generous thinking budget
Thinking budget control: The serving engine needs to implement a token budget for the block
- stopping generation of thinking tokens after a threshold and forcing the model to transition to the actual response. This requires modifying the generation loop to detect or enforce a token limit within the thinking block.
Model level training: For 'reasoning_effort' to be truly meaningful (not just truncating thoughts), the model would need to be post-trained with varying levels of chain-of-thought depth:
- Fine-tune on examples with short, medium, and long reasoning traces, each labeled with the corresponding effort level
- Train the model to condition its reasoning depth on an effort token or system prompt instruction
- This is how models like Claude natively support reasoning effort — it's baked into the training, not bolted on at serving time

Downloads last month: 13

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for hi1hello/FriendliAI-broken-model-fixed

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(2146)

this model