Instructions to use ajaxdavis/alpha-chat-v11-m300-experimental with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ajaxdavis/alpha-chat-v11-m300-experimental with Transformers:

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

pipe = pipeline("text-generation", model="ajaxdavis/alpha-chat-v11-m300-experimental")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ajaxdavis/alpha-chat-v11-m300-experimental")
model = AutoModelForCausalLM.from_pretrained("ajaxdavis/alpha-chat-v11-m300-experimental", 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 ajaxdavis/alpha-chat-v11-m300-experimental with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ajaxdavis/alpha-chat-v11-m300-experimental"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ajaxdavis/alpha-chat-v11-m300-experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ajaxdavis/alpha-chat-v11-m300-experimental

SGLang

How to use ajaxdavis/alpha-chat-v11-m300-experimental 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 "ajaxdavis/alpha-chat-v11-m300-experimental" \
    --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": "ajaxdavis/alpha-chat-v11-m300-experimental",
		"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 "ajaxdavis/alpha-chat-v11-m300-experimental" \
        --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": "ajaxdavis/alpha-chat-v11-m300-experimental",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ajaxdavis/alpha-chat-v11-m300-experimental with Docker Model Runner:
```
docker model run hf.co/ajaxdavis/alpha-chat-v11-m300-experimental
```

Alpha chat v11-m300 experimental

This is a versioned experimental checkpoint published for independent evaluation. It did not beat Alpha's V8 development reference and is not the selected production checkpoint.

V11 tested an all-token causal-language-modeling bridge over 10,862 reviewed synthetic conversations. The conversation candidates were generated with GPT-5.4 and independently reviewed with GPT-5.5. The model began from the V8 step-200 checkpoint; the architecture, tokenizer, chat template, and inference renderer were kept fixed. Symbiogenesis was disabled.

Measured result

On the unchanged 615-conversation development diagnostic, this checkpoint produced 615 nonempty, EOS-terminated responses, with 12 detected degenerate loops and a mean four-gram repeat rate of 0.0120652. In a reference-blinded GPT-5.5 review of 100 conversations, it received 15 PASS, 11 BORDERLINE, and 74 FAIL judgments. The V8 reference received 16 PASS, 9 BORDERLINE, and 75 FAIL judgments and ranked first overall. The reviewer selected no candidate as conversationally competent.

This artifact is therefore useful as a negative result: full-dialogue token supervision improved response initiation and stopping, but did not produce a reliable semantic gain and increased repetition relative to V8.

Exact identity

Native checkpoint step: 300
Native checkpoint SHA-256: 6226c1443741058089f110b89dfa341e0325851098d3aaf049a501c1ca3393f9
Tokenizer SHA-256: c310343a185aecb572b8b6568b55179df248f4adec009d14a9496da354090b24
Source commit used for training: 1dfdb813ecdaa72bfa51ec07757f4265372c03a7
Blinded review SHA-256: 29355fb8a4e8093472b08f0bb4438964383749c00dd2be8faf625ea468a40a1a
Quality gate: FAIL

Usage

from transformers import pipeline

chat = pipeline("text-generation", model="ajaxdavis/alpha-chat-v11-m300-experimental")
result = chat([{"role": "user", "content": "Hello. What are you thinking about?"}], max_new_tokens=64)
print(result[0]["generated_text"][-1]["content"])

The export uses standard LlamaForCausalLM files and requires no custom model code. Its exact chat template is included in chat_template.jinja. Do not interpret nonempty output or a low training loss as evidence of conversational competence.

The source, experiment contract, evaluation tools, and outcome record live in the Alpha2 repository.

Downloads last month: 12

Safetensors

Model size

57.7M params

Tensor type

F32