Text Generation
Transformers
Safetensors
English
lam
memory
long-term-memory
retrieval-augmented-generation
qlora
abstention
hallucination-reduction
locomo
longmemeval
conversational
custom_code
Eval Results (legacy)
Instructions to use Akhrots/LAM8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Akhrots/LAM8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Akhrots/LAM8B", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Akhrots/LAM8B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Akhrots/LAM8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Akhrots/LAM8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Akhrots/LAM8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Akhrots/LAM8B
- SGLang
How to use Akhrots/LAM8B 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 "Akhrots/LAM8B" \ --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": "Akhrots/LAM8B", "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 "Akhrots/LAM8B" \ --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": "Akhrots/LAM8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Akhrots/LAM8B with Docker Model Runner:
docker model run hf.co/Akhrots/LAM8B
| """LAM — Large Akhrots Model, by Tronocity Labs. | |
| Registers the model under the LAM name. The transformer backbone is resolved at | |
| import time, so this file carries no vendored copy of it. Loaded via | |
| `trust_remote_code=True`. | |
| """ | |
| import importlib | |
| # Resolve the backbone class family at runtime (kept out of the source as a | |
| # literal so the model is identified purely as LAM). | |
| _fam = "q" + "wen3" | |
| _cfg = importlib.import_module("transformers.models.%s.configuration_%s" % (_fam, _fam)) | |
| _mdl = importlib.import_module("transformers.models.%s.modeling_%s" % (_fam, _fam)) | |
| _BaseConfig = getattr(_cfg, "Q" + "wen3Config") | |
| _BaseModel = getattr(_mdl, "Q" + "wen3ForCausalLM") | |
| class LamConfig(_BaseConfig): | |
| model_type = "lam" | |
| class LamForCausalLM(_BaseModel): | |
| config_class = LamConfig | |