Text Generation
Transformers
Safetensors
llama
deepseek
int4
vllm
llmcompressor
conversational
text-generation-inference
compressed-tensors
Instructions to use RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16") model = AutoModelForCausalLM.from_pretrained("RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16") 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
- vLLM
How to use RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16
- SGLang
How to use RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 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 "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16" \ --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": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "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 "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16" \ --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": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 with Docker Model Runner:
docker model run hf.co/RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16
| { | |
| "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 28672, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": "group", | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": 128, | |
| "num_bits": 4, | |
| "observer": "mse", | |
| "observer_kwargs": {}, | |
| "strategy": "group", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": 2.0909603777162826, | |
| "ignore": [ | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": { | |
| "format": "dense", | |
| "global_sparsity": 0.1397568369886873, | |
| "ignore": [ | |
| "model.layers.0.self_attn.o_proj", | |
| "model.layers.0.mlp.gate_proj", | |
| "model.layers.0.mlp.up_proj", | |
| "model.layers.0.mlp.down_proj", | |
| "model.layers.1.self_attn.q_proj", | |
| "model.layers.1.self_attn.k_proj", | |
| "model.layers.1.self_attn.v_proj", | |
| "model.layers.1.self_attn.o_proj", | |
| "model.layers.1.mlp.gate_proj", | |
| "model.layers.1.mlp.up_proj", | |
| "model.layers.1.mlp.down_proj", | |
| "model.layers.2.self_attn.q_proj", | |
| "model.layers.2.self_attn.k_proj", | |
| "model.layers.2.self_attn.v_proj", | |
| "model.layers.2.self_attn.o_proj", | |
| "model.layers.2.mlp.gate_proj", | |
| "model.layers.2.mlp.up_proj", | |
| "model.layers.2.mlp.down_proj", | |
| "model.layers.3.self_attn.q_proj", | |
| "model.layers.3.self_attn.k_proj", | |
| "model.layers.3.self_attn.v_proj", | |
| "model.layers.3.self_attn.o_proj", | |
| "model.layers.3.mlp.gate_proj", | |
| "model.layers.3.mlp.up_proj", | |
| "model.layers.3.mlp.down_proj", | |
| "model.layers.4.self_attn.q_proj", | |
| "model.layers.4.self_attn.k_proj", | |
| "model.layers.4.self_attn.v_proj", | |
| "model.layers.4.self_attn.o_proj", | |
| "model.layers.4.mlp.gate_proj", | |
| "model.layers.4.mlp.up_proj", | |
| "model.layers.4.mlp.down_proj", | |
| "model.layers.5.self_attn.q_proj", | |
| "model.layers.5.self_attn.k_proj", | |
| "model.layers.5.self_attn.v_proj", | |
| "model.layers.5.self_attn.o_proj", | |
| "model.layers.5.mlp.gate_proj", | |
| "model.layers.5.mlp.up_proj", | |
| "model.layers.5.mlp.down_proj", | |
| "model.layers.6.self_attn.q_proj", | |
| "model.layers.6.self_attn.k_proj", | |
| "model.layers.6.self_attn.v_proj", | |
| "model.layers.6.self_attn.o_proj", | |
| "model.layers.6.mlp.gate_proj", | |
| "model.layers.6.mlp.up_proj", | |
| "model.layers.6.mlp.down_proj", | |
| "model.layers.7.self_attn.q_proj", | |
| "model.layers.7.self_attn.k_proj", | |
| "model.layers.7.self_attn.v_proj", | |
| "model.layers.7.self_attn.o_proj", | |
| "model.layers.7.mlp.gate_proj", | |
| "model.layers.7.mlp.up_proj", | |
| "model.layers.7.mlp.down_proj", | |
| "model.layers.8.self_attn.q_proj", | |
| "model.layers.8.self_attn.k_proj", | |
| "model.layers.8.self_attn.v_proj", | |
| "model.layers.8.self_attn.o_proj", | |
| "model.layers.8.mlp.gate_proj", | |
| "model.layers.8.mlp.up_proj", | |
| "model.layers.8.mlp.down_proj", | |
| "model.layers.9.self_attn.q_proj", | |
| "model.layers.9.self_attn.k_proj", | |
| "model.layers.9.self_attn.v_proj", | |
| "model.layers.9.self_attn.o_proj", | |
| "model.layers.9.mlp.gate_proj", | |
| "model.layers.9.mlp.up_proj", | |
| "model.layers.9.mlp.down_proj", | |
| "model.layers.10.self_attn.q_proj", | |
| "model.layers.10.self_attn.k_proj", | |
| "model.layers.10.self_attn.v_proj", | |
| "model.layers.10.self_attn.o_proj", | |
| "model.layers.10.mlp.gate_proj", | |
| "model.layers.10.mlp.up_proj", | |
| "model.layers.10.mlp.down_proj", | |
| "model.layers.11.self_attn.q_proj", | |
| "model.layers.11.self_attn.k_proj", | |
| "model.layers.11.self_attn.v_proj", | |
| "model.layers.11.self_attn.o_proj", | |
| "model.layers.11.mlp.gate_proj", | |
| "model.layers.11.mlp.up_proj", | |
| "model.layers.11.mlp.down_proj", | |
| "model.layers.12.self_attn.q_proj", | |
| "model.layers.12.self_attn.k_proj", | |
| "model.layers.12.self_attn.v_proj", | |
| "model.layers.12.self_attn.o_proj", | |
| "model.layers.12.mlp.gate_proj", | |
| "model.layers.12.mlp.up_proj", | |
| "model.layers.12.mlp.down_proj", | |
| "model.layers.13.self_attn.q_proj", | |
| "model.layers.13.self_attn.k_proj", | |
| "model.layers.13.self_attn.v_proj", | |
| "model.layers.13.self_attn.o_proj", | |
| "model.layers.13.mlp.gate_proj", | |
| "model.layers.13.mlp.up_proj", | |
| "model.layers.13.mlp.down_proj", | |
| "model.layers.14.self_attn.q_proj", | |
| "model.layers.14.self_attn.k_proj", | |
| "model.layers.14.self_attn.v_proj", | |
| "model.layers.14.self_attn.o_proj", | |
| "model.layers.14.mlp.gate_proj", | |
| "model.layers.14.mlp.up_proj", | |
| "model.layers.14.mlp.down_proj", | |
| "model.layers.15.self_attn.q_proj", | |
| "model.layers.15.self_attn.k_proj", | |
| "model.layers.15.self_attn.v_proj", | |
| "model.layers.15.self_attn.o_proj", | |
| "model.layers.15.mlp.gate_proj", | |
| "model.layers.15.mlp.up_proj", | |
| "model.layers.15.mlp.down_proj", | |
| "model.layers.16.self_attn.q_proj", | |
| "model.layers.16.self_attn.k_proj", | |
| "model.layers.16.self_attn.v_proj", | |
| "model.layers.16.self_attn.o_proj", | |
| "model.layers.16.mlp.gate_proj", | |
| "model.layers.16.mlp.up_proj", | |
| "model.layers.16.mlp.down_proj", | |
| "model.layers.17.self_attn.q_proj", | |
| "model.layers.17.self_attn.k_proj", | |
| "model.layers.17.self_attn.v_proj", | |
| "model.layers.17.self_attn.o_proj", | |
| "model.layers.17.mlp.gate_proj", | |
| "model.layers.17.mlp.up_proj", | |
| "model.layers.17.mlp.down_proj", | |
| "model.layers.18.self_attn.q_proj", | |
| "model.layers.18.self_attn.k_proj", | |
| "model.layers.18.self_attn.v_proj", | |
| "model.layers.18.self_attn.o_proj", | |
| "model.layers.18.mlp.gate_proj", | |
| "model.layers.18.mlp.up_proj", | |
| "model.layers.18.mlp.down_proj", | |
| "model.layers.19.self_attn.q_proj", | |
| "model.layers.19.self_attn.k_proj", | |
| "model.layers.19.self_attn.v_proj", | |
| "model.layers.19.self_attn.o_proj", | |
| "model.layers.19.mlp.gate_proj", | |
| "model.layers.19.mlp.up_proj", | |
| "model.layers.19.mlp.down_proj", | |
| "model.layers.20.self_attn.q_proj", | |
| "model.layers.20.self_attn.k_proj", | |
| "model.layers.20.self_attn.v_proj", | |
| "model.layers.20.self_attn.o_proj", | |
| "model.layers.20.mlp.gate_proj", | |
| "model.layers.20.mlp.up_proj", | |
| "model.layers.20.mlp.down_proj", | |
| "model.layers.21.self_attn.q_proj", | |
| "model.layers.21.self_attn.k_proj", | |
| "model.layers.21.self_attn.v_proj", | |
| "model.layers.21.self_attn.o_proj", | |
| "model.layers.21.mlp.gate_proj", | |
| "model.layers.21.mlp.up_proj", | |
| "model.layers.21.mlp.down_proj", | |
| "model.layers.22.self_attn.q_proj", | |
| "model.layers.22.self_attn.k_proj", | |
| "model.layers.22.self_attn.v_proj", | |
| "model.layers.22.self_attn.o_proj", | |
| "model.layers.22.mlp.gate_proj", | |
| "model.layers.22.mlp.up_proj", | |
| "model.layers.22.mlp.down_proj", | |
| "model.layers.23.self_attn.q_proj", | |
| "model.layers.23.self_attn.k_proj", | |
| "model.layers.23.self_attn.v_proj", | |
| "model.layers.23.self_attn.o_proj", | |
| "model.layers.23.mlp.gate_proj", | |
| "model.layers.23.mlp.up_proj", | |
| "model.layers.23.mlp.down_proj", | |
| "model.layers.24.self_attn.q_proj", | |
| "model.layers.24.self_attn.k_proj", | |
| "model.layers.24.self_attn.v_proj", | |
| "model.layers.24.self_attn.o_proj", | |
| "model.layers.24.mlp.gate_proj", | |
| "model.layers.24.mlp.up_proj", | |
| "model.layers.24.mlp.down_proj", | |
| "model.layers.25.self_attn.q_proj", | |
| "model.layers.25.self_attn.k_proj", | |
| "model.layers.25.self_attn.v_proj", | |
| "model.layers.25.self_attn.o_proj", | |
| "model.layers.25.mlp.gate_proj", | |
| "model.layers.25.mlp.up_proj", | |
| "model.layers.25.mlp.down_proj", | |
| "model.layers.26.self_attn.q_proj", | |
| "model.layers.26.self_attn.k_proj", | |
| "model.layers.26.self_attn.v_proj", | |
| "model.layers.26.self_attn.o_proj", | |
| "model.layers.26.mlp.gate_proj", | |
| "model.layers.26.mlp.up_proj", | |
| "model.layers.26.mlp.down_proj", | |
| "model.layers.27.self_attn.q_proj", | |
| "model.layers.27.self_attn.k_proj", | |
| "model.layers.27.self_attn.v_proj", | |
| "model.layers.27.self_attn.o_proj", | |
| "model.layers.27.mlp.gate_proj", | |
| "model.layers.27.mlp.up_proj", | |
| "model.layers.27.mlp.down_proj", | |
| "model.layers.28.self_attn.q_proj", | |
| "model.layers.28.self_attn.k_proj", | |
| "model.layers.28.self_attn.v_proj", | |
| "model.layers.28.self_attn.o_proj", | |
| "model.layers.28.mlp.gate_proj", | |
| "model.layers.28.mlp.up_proj", | |
| "model.layers.28.mlp.down_proj", | |
| "model.layers.29.self_attn.q_proj", | |
| "model.layers.29.self_attn.k_proj", | |
| "model.layers.29.self_attn.v_proj", | |
| "model.layers.29.self_attn.o_proj", | |
| "model.layers.29.mlp.gate_proj", | |
| "model.layers.29.mlp.up_proj", | |
| "model.layers.29.mlp.down_proj", | |
| "model.layers.30.self_attn.q_proj", | |
| "model.layers.30.self_attn.k_proj", | |
| "model.layers.30.self_attn.v_proj", | |
| "model.layers.30.self_attn.o_proj", | |
| "model.layers.30.mlp.gate_proj", | |
| "model.layers.30.mlp.up_proj", | |
| "model.layers.30.mlp.down_proj", | |
| "model.layers.31.self_attn.q_proj", | |
| "model.layers.31.self_attn.k_proj", | |
| "model.layers.31.self_attn.v_proj", | |
| "model.layers.31.self_attn.o_proj", | |
| "model.layers.31.mlp.gate_proj", | |
| "model.layers.31.mlp.up_proj", | |
| "model.layers.31.mlp.down_proj", | |
| "model.layers.32.self_attn.q_proj", | |
| "model.layers.32.self_attn.k_proj", | |
| "model.layers.32.self_attn.v_proj", | |
| "model.layers.32.self_attn.o_proj", | |
| "model.layers.32.mlp.gate_proj", | |
| "model.layers.32.mlp.up_proj", | |
| "model.layers.32.mlp.down_proj", | |
| "model.layers.33.self_attn.q_proj", | |
| "model.layers.33.self_attn.k_proj", | |
| "model.layers.33.self_attn.v_proj", | |
| "model.layers.33.self_attn.o_proj", | |
| "model.layers.33.mlp.gate_proj", | |
| "model.layers.33.mlp.up_proj", | |
| "model.layers.33.mlp.down_proj", | |
| "model.layers.34.self_attn.q_proj", | |
| "model.layers.34.self_attn.k_proj", | |
| "model.layers.34.self_attn.v_proj", | |
| "model.layers.34.self_attn.o_proj", | |
| "model.layers.34.mlp.gate_proj", | |
| "model.layers.34.mlp.up_proj", | |
| "model.layers.34.mlp.down_proj", | |
| "model.layers.35.self_attn.q_proj", | |
| "model.layers.35.self_attn.k_proj", | |
| "model.layers.35.self_attn.v_proj", | |
| "model.layers.35.self_attn.o_proj", | |
| "model.layers.35.mlp.gate_proj", | |
| "model.layers.35.mlp.up_proj", | |
| "model.layers.35.mlp.down_proj", | |
| "model.layers.36.self_attn.q_proj", | |
| "model.layers.36.self_attn.k_proj", | |
| "model.layers.36.self_attn.v_proj", | |
| "model.layers.36.self_attn.o_proj", | |
| "model.layers.36.mlp.gate_proj", | |
| "model.layers.36.mlp.up_proj", | |
| "model.layers.36.mlp.down_proj", | |
| "model.layers.37.self_attn.q_proj", | |
| "model.layers.37.self_attn.k_proj", | |
| "model.layers.37.self_attn.v_proj", | |
| "model.layers.37.self_attn.o_proj", | |
| "model.layers.37.mlp.gate_proj", | |
| "model.layers.37.mlp.up_proj", | |
| "model.layers.37.mlp.down_proj", | |
| "model.layers.38.self_attn.q_proj", | |
| "model.layers.38.self_attn.k_proj", | |
| "model.layers.38.self_attn.v_proj", | |
| "model.layers.38.self_attn.o_proj", | |
| "model.layers.38.mlp.gate_proj", | |
| "model.layers.38.mlp.up_proj", | |
| "model.layers.38.mlp.down_proj", | |
| "model.layers.39.self_attn.q_proj", | |
| "model.layers.39.self_attn.k_proj", | |
| "model.layers.39.self_attn.v_proj", | |
| "model.layers.39.self_attn.o_proj", | |
| "model.layers.39.mlp.gate_proj", | |
| "model.layers.39.mlp.up_proj", | |
| "model.layers.39.mlp.down_proj", | |
| "model.layers.40.self_attn.q_proj", | |
| "model.layers.40.self_attn.k_proj", | |
| "model.layers.40.self_attn.v_proj", | |
| "model.layers.40.self_attn.o_proj", | |
| "model.layers.40.mlp.gate_proj", | |
| "model.layers.40.mlp.up_proj", | |
| "model.layers.40.mlp.down_proj", | |
| "model.layers.41.self_attn.q_proj", | |
| "model.layers.41.self_attn.k_proj", | |
| "model.layers.41.self_attn.v_proj", | |
| "model.layers.41.self_attn.o_proj", | |
| "model.layers.41.mlp.gate_proj", | |
| "model.layers.41.mlp.up_proj", | |
| "model.layers.41.mlp.down_proj", | |
| "model.layers.42.self_attn.q_proj", | |
| "model.layers.42.self_attn.k_proj", | |
| "model.layers.42.self_attn.v_proj", | |
| "model.layers.42.self_attn.o_proj", | |
| "model.layers.42.mlp.gate_proj", | |
| "model.layers.42.mlp.up_proj", | |
| "model.layers.42.mlp.down_proj", | |
| "model.layers.43.self_attn.q_proj", | |
| "model.layers.43.self_attn.k_proj", | |
| "model.layers.43.self_attn.v_proj", | |
| "model.layers.43.self_attn.o_proj", | |
| "model.layers.43.mlp.gate_proj", | |
| "model.layers.43.mlp.up_proj", | |
| "model.layers.43.mlp.down_proj", | |
| "model.layers.44.self_attn.q_proj", | |
| "model.layers.44.self_attn.k_proj", | |
| "model.layers.44.self_attn.v_proj", | |
| "model.layers.44.self_attn.o_proj", | |
| "model.layers.44.mlp.gate_proj", | |
| "model.layers.44.mlp.up_proj", | |
| "model.layers.44.mlp.down_proj", | |
| "model.layers.45.self_attn.q_proj", | |
| "model.layers.45.self_attn.k_proj", | |
| "model.layers.45.self_attn.v_proj", | |
| "model.layers.45.self_attn.o_proj", | |
| "model.layers.45.mlp.gate_proj", | |
| "model.layers.45.mlp.up_proj", | |
| "model.layers.45.mlp.down_proj", | |
| "model.layers.46.self_attn.q_proj", | |
| "model.layers.46.self_attn.k_proj", | |
| "model.layers.46.self_attn.v_proj", | |
| "model.layers.46.self_attn.o_proj", | |
| "model.layers.46.mlp.gate_proj", | |
| "model.layers.46.mlp.up_proj", | |
| "model.layers.46.mlp.down_proj", | |
| "model.layers.47.self_attn.q_proj", | |
| "model.layers.47.self_attn.k_proj", | |
| "model.layers.47.self_attn.v_proj", | |
| "model.layers.47.self_attn.o_proj", | |
| "model.layers.47.mlp.gate_proj", | |
| "model.layers.47.mlp.up_proj", | |
| "model.layers.47.mlp.down_proj", | |
| "model.layers.48.self_attn.q_proj", | |
| "model.layers.48.self_attn.k_proj", | |
| "model.layers.48.self_attn.v_proj", | |
| "model.layers.48.self_attn.o_proj", | |
| "model.layers.48.mlp.gate_proj", | |
| "model.layers.48.mlp.up_proj", | |
| "model.layers.48.mlp.down_proj", | |
| "model.layers.49.self_attn.q_proj", | |
| "model.layers.49.self_attn.k_proj", | |
| "model.layers.49.self_attn.v_proj", | |
| "model.layers.49.self_attn.o_proj", | |
| "model.layers.49.mlp.gate_proj", | |
| "model.layers.49.mlp.up_proj", | |
| "model.layers.49.mlp.down_proj", | |
| "model.layers.50.self_attn.q_proj", | |
| "model.layers.50.self_attn.k_proj", | |
| "model.layers.50.self_attn.v_proj", | |
| "model.layers.50.self_attn.o_proj", | |
| "model.layers.50.mlp.gate_proj", | |
| "model.layers.50.mlp.up_proj", | |
| "model.layers.50.mlp.down_proj", | |
| "model.layers.51.self_attn.q_proj", | |
| "model.layers.51.self_attn.k_proj", | |
| "model.layers.51.self_attn.v_proj", | |
| "model.layers.51.self_attn.o_proj", | |
| "model.layers.51.mlp.gate_proj", | |
| "model.layers.51.mlp.up_proj", | |
| "model.layers.51.mlp.down_proj", | |
| "model.layers.52.self_attn.q_proj", | |
| "model.layers.52.self_attn.k_proj", | |
| "model.layers.52.self_attn.v_proj", | |
| "model.layers.52.self_attn.o_proj", | |
| "model.layers.52.mlp.gate_proj", | |
| "model.layers.52.mlp.up_proj", | |
| "model.layers.52.mlp.down_proj", | |
| "model.layers.53.self_attn.q_proj", | |
| "model.layers.53.self_attn.k_proj", | |
| "model.layers.53.self_attn.v_proj", | |
| "model.layers.53.self_attn.o_proj", | |
| "model.layers.53.mlp.gate_proj", | |
| "model.layers.53.mlp.up_proj", | |
| "model.layers.53.mlp.down_proj", | |
| "model.layers.54.self_attn.q_proj", | |
| "model.layers.54.self_attn.k_proj", | |
| "model.layers.54.self_attn.v_proj", | |
| "model.layers.54.self_attn.o_proj", | |
| "model.layers.54.mlp.gate_proj", | |
| "model.layers.54.mlp.up_proj", | |
| "model.layers.54.mlp.down_proj", | |
| "model.layers.55.self_attn.q_proj", | |
| "model.layers.55.self_attn.k_proj", | |
| "model.layers.55.self_attn.v_proj", | |
| "model.layers.55.self_attn.o_proj", | |
| "model.layers.55.mlp.gate_proj", | |
| "model.layers.55.mlp.up_proj", | |
| "model.layers.55.mlp.down_proj", | |
| "model.layers.56.self_attn.q_proj", | |
| "model.layers.56.self_attn.k_proj", | |
| "model.layers.56.self_attn.v_proj", | |
| "model.layers.56.self_attn.o_proj", | |
| "model.layers.56.mlp.gate_proj", | |
| "model.layers.56.mlp.up_proj", | |
| "model.layers.56.mlp.down_proj", | |
| "model.layers.57.self_attn.q_proj", | |
| "model.layers.57.self_attn.k_proj", | |
| "model.layers.57.self_attn.v_proj", | |
| "model.layers.57.self_attn.o_proj", | |
| "model.layers.57.mlp.gate_proj", | |
| "model.layers.57.mlp.up_proj", | |
| "model.layers.57.mlp.down_proj", | |
| "model.layers.58.self_attn.q_proj", | |
| "model.layers.58.self_attn.k_proj", | |
| "model.layers.58.self_attn.v_proj", | |
| "model.layers.58.self_attn.o_proj", | |
| "model.layers.58.mlp.gate_proj", | |
| "model.layers.58.mlp.up_proj", | |
| "model.layers.58.mlp.down_proj", | |
| "model.layers.59.self_attn.q_proj", | |
| "model.layers.59.self_attn.k_proj", | |
| "model.layers.59.self_attn.v_proj", | |
| "model.layers.59.self_attn.o_proj", | |
| "model.layers.59.mlp.gate_proj", | |
| "model.layers.59.mlp.up_proj", | |
| "model.layers.59.mlp.down_proj", | |
| "model.layers.60.self_attn.q_proj", | |
| "model.layers.60.self_attn.k_proj", | |
| "model.layers.60.self_attn.v_proj", | |
| "model.layers.60.self_attn.o_proj", | |
| "model.layers.60.mlp.gate_proj", | |
| "model.layers.60.mlp.up_proj", | |
| "model.layers.60.mlp.down_proj", | |
| "model.layers.61.self_attn.q_proj", | |
| "model.layers.61.self_attn.k_proj", | |
| "model.layers.61.self_attn.v_proj", | |
| "model.layers.61.self_attn.o_proj", | |
| "model.layers.61.mlp.gate_proj", | |
| "model.layers.61.mlp.up_proj", | |
| "model.layers.61.mlp.down_proj", | |
| "model.layers.62.self_attn.q_proj", | |
| "model.layers.62.self_attn.k_proj", | |
| "model.layers.62.self_attn.v_proj", | |
| "model.layers.62.self_attn.o_proj", | |
| "model.layers.62.mlp.gate_proj", | |
| "model.layers.62.mlp.up_proj", | |
| "model.layers.62.mlp.down_proj", | |
| "model.layers.63.self_attn.q_proj", | |
| "model.layers.63.self_attn.k_proj", | |
| "model.layers.63.self_attn.v_proj", | |
| "model.layers.63.self_attn.o_proj", | |
| "model.layers.63.mlp.gate_proj", | |
| "model.layers.63.mlp.up_proj", | |
| "model.layers.63.mlp.down_proj", | |
| "model.layers.64.self_attn.q_proj", | |
| "model.layers.64.self_attn.k_proj", | |
| "model.layers.64.self_attn.v_proj", | |
| "model.layers.64.self_attn.o_proj", | |
| "model.layers.64.mlp.gate_proj", | |
| "model.layers.64.mlp.up_proj", | |
| "model.layers.64.mlp.down_proj", | |
| "model.layers.65.self_attn.q_proj", | |
| "model.layers.65.self_attn.k_proj", | |
| "model.layers.65.self_attn.v_proj", | |
| "model.layers.65.self_attn.o_proj", | |
| "model.layers.65.mlp.gate_proj", | |
| "model.layers.65.mlp.up_proj", | |
| "model.layers.65.mlp.down_proj", | |
| "model.layers.66.self_attn.q_proj", | |
| "model.layers.66.self_attn.k_proj", | |
| "model.layers.66.self_attn.v_proj", | |
| "model.layers.66.self_attn.o_proj", | |
| "model.layers.66.mlp.gate_proj", | |
| "model.layers.66.mlp.up_proj", | |
| "model.layers.66.mlp.down_proj", | |
| "model.layers.67.self_attn.q_proj", | |
| "model.layers.67.self_attn.k_proj", | |
| "model.layers.67.self_attn.v_proj", | |
| "model.layers.67.self_attn.o_proj", | |
| "model.layers.67.mlp.gate_proj", | |
| "model.layers.67.mlp.up_proj", | |
| "model.layers.67.mlp.down_proj", | |
| "model.layers.68.self_attn.q_proj", | |
| "model.layers.68.self_attn.k_proj", | |
| "model.layers.68.self_attn.v_proj", | |
| "model.layers.68.self_attn.o_proj", | |
| "model.layers.68.mlp.gate_proj", | |
| "model.layers.68.mlp.up_proj", | |
| "model.layers.68.mlp.down_proj", | |
| "model.layers.69.self_attn.q_proj", | |
| "model.layers.69.self_attn.k_proj", | |
| "model.layers.69.self_attn.v_proj", | |
| "model.layers.69.self_attn.o_proj", | |
| "model.layers.69.mlp.gate_proj", | |
| "model.layers.69.mlp.up_proj", | |
| "model.layers.69.mlp.down_proj", | |
| "model.layers.70.self_attn.q_proj", | |
| "model.layers.70.self_attn.k_proj", | |
| "model.layers.70.self_attn.v_proj", | |
| "model.layers.70.self_attn.o_proj", | |
| "model.layers.70.mlp.gate_proj", | |
| "model.layers.70.mlp.up_proj", | |
| "model.layers.70.mlp.down_proj", | |
| "model.layers.71.self_attn.q_proj", | |
| "model.layers.71.self_attn.k_proj", | |
| "model.layers.71.self_attn.v_proj", | |
| "model.layers.71.self_attn.o_proj", | |
| "model.layers.71.mlp.gate_proj", | |
| "model.layers.71.mlp.up_proj", | |
| "model.layers.71.mlp.down_proj", | |
| "model.layers.72.self_attn.q_proj", | |
| "model.layers.72.self_attn.k_proj", | |
| "model.layers.72.self_attn.v_proj", | |
| "model.layers.72.self_attn.o_proj", | |
| "model.layers.72.mlp.gate_proj", | |
| "model.layers.72.mlp.up_proj", | |
| "model.layers.72.mlp.down_proj", | |
| "model.layers.73.self_attn.q_proj", | |
| "model.layers.73.self_attn.k_proj", | |
| "model.layers.73.self_attn.v_proj", | |
| "model.layers.73.self_attn.o_proj", | |
| "model.layers.73.mlp.gate_proj", | |
| "model.layers.73.mlp.up_proj", | |
| "model.layers.73.mlp.down_proj", | |
| "model.layers.74.self_attn.q_proj", | |
| "model.layers.74.self_attn.k_proj", | |
| "model.layers.74.self_attn.v_proj", | |
| "model.layers.74.self_attn.o_proj", | |
| "model.layers.74.mlp.gate_proj", | |
| "model.layers.74.mlp.up_proj", | |
| "model.layers.74.mlp.down_proj", | |
| "model.layers.75.self_attn.q_proj", | |
| "model.layers.75.self_attn.k_proj", | |
| "model.layers.75.self_attn.v_proj", | |
| "model.layers.75.self_attn.o_proj", | |
| "model.layers.75.mlp.gate_proj", | |
| "model.layers.75.mlp.up_proj", | |
| "model.layers.75.mlp.down_proj", | |
| "model.layers.76.self_attn.q_proj", | |
| "model.layers.76.self_attn.k_proj", | |
| "model.layers.76.self_attn.v_proj", | |
| "model.layers.76.self_attn.o_proj", | |
| "model.layers.76.mlp.gate_proj", | |
| "model.layers.76.mlp.up_proj", | |
| "model.layers.76.mlp.down_proj", | |
| "model.layers.77.self_attn.q_proj", | |
| "model.layers.77.self_attn.k_proj", | |
| "model.layers.77.self_attn.v_proj", | |
| "model.layers.77.self_attn.o_proj", | |
| "model.layers.77.mlp.gate_proj", | |
| "model.layers.77.mlp.up_proj", | |
| "model.layers.77.mlp.down_proj", | |
| "model.layers.78.self_attn.q_proj", | |
| "model.layers.78.self_attn.k_proj", | |
| "model.layers.78.self_attn.v_proj", | |
| "model.layers.78.self_attn.o_proj", | |
| "model.layers.78.mlp.gate_proj", | |
| "model.layers.78.mlp.up_proj", | |
| "model.layers.78.mlp.down_proj", | |
| "model.layers.79.self_attn.q_proj", | |
| "model.layers.79.self_attn.k_proj", | |
| "model.layers.79.self_attn.v_proj", | |
| "model.layers.79.self_attn.o_proj", | |
| "model.layers.79.mlp.gate_proj", | |
| "model.layers.79.mlp.up_proj", | |
| "model.layers.79.mlp.down_proj", | |
| "lm_head" | |
| ], | |
| "registry_requires_subclass": false, | |
| "sparsity_structure": "unstructured", | |
| "targets": [ | |
| "model.layers.0.self_attn.q_proj", | |
| "model.layers.0.self_attn.k_proj", | |
| "model.layers.0.self_attn.v_proj" | |
| ] | |
| } | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.48.0", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } |