Instructions to use xfcxcxcdfdfd/1xd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xfcxcxcdfdfd/1xd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xfcxcxcdfdfd/1xd") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("xfcxcxcdfdfd/1xd") model = AutoModelForCausalLM.from_pretrained("xfcxcxcdfdfd/1xd") 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 xfcxcxcdfdfd/1xd with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xfcxcxcdfdfd/1xd" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xfcxcxcdfdfd/1xd", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/xfcxcxcdfdfd/1xd
- SGLang
How to use xfcxcxcdfdfd/1xd 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 "xfcxcxcdfdfd/1xd" \ --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": "xfcxcxcdfdfd/1xd", "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 "xfcxcxcdfdfd/1xd" \ --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": "xfcxcxcdfdfd/1xd", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use xfcxcxcdfdfd/1xd with Docker Model Runner:
docker model run hf.co/xfcxcxcdfdfd/1xd
Adding `safetensors` variant of this model
#2
by SFconvertbot - opened
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99e5927c97e0c451cccd507b3a8af2cc6aaa585fe2293870bc33fb7136516a44
|
| 3 |
+
size 4838627416
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8250cf0b5f517f8ec9d0b379b9a2ad3d2e43ec8aba646b454b47fd9a3ad530ed
|
| 3 |
+
size 1651557152
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6490177552
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"draft_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"draft_model.emotion_vector": "model-00001-of-00002.safetensors",
|
| 8 |
+
"draft_model.lm_head.weight": "model-00002-of-00002.safetensors",
|
| 9 |
+
"draft_model.memory_keys": "model-00001-of-00002.safetensors",
|
| 10 |
+
"draft_model.memory_values": "model-00001-of-00002.safetensors",
|
| 11 |
+
"draft_model.norm.bias": "model-00001-of-00002.safetensors",
|
| 12 |
+
"draft_model.norm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"draft_model.prediction_head.bias": "model-00002-of-00002.safetensors",
|
| 14 |
+
"draft_model.prediction_head.weight": "model-00002-of-00002.safetensors",
|
| 15 |
+
"draft_model.response_selector.bias": "model-00002-of-00002.safetensors",
|
| 16 |
+
"draft_model.response_selector.weight": "model-00002-of-00002.safetensors",
|
| 17 |
+
"draft_model.shared_layer.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"draft_model.shared_layer.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"draft_model.shared_layer.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"draft_model.shared_layer.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"draft_model.shared_layer.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"draft_model.shared_layer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"draft_model.shared_layer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"draft_model.shared_layer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"draft_model.shared_layer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"draft_model.simulation_head.bias": "model-00002-of-00002.safetensors",
|
| 27 |
+
"draft_model.simulation_head.weight": "model-00002-of-00002.safetensors",
|
| 28 |
+
"draft_model.stimuli_vector": "model-00001-of-00002.safetensors",
|
| 29 |
+
"draft_model.unique_layer.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"draft_model.unique_layer.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"draft_model.unique_layer.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"draft_model.unique_layer.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"draft_model.unique_layer.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"draft_model.unique_layer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"draft_model.unique_layer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"draft_model.unique_layer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"draft_model.unique_layer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"emotion_vector": "model-00001-of-00002.safetensors",
|
| 40 |
+
"lm_head.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"memory_keys": "model-00001-of-00002.safetensors",
|
| 42 |
+
"memory_values": "model-00001-of-00002.safetensors",
|
| 43 |
+
"norm.bias": "model-00001-of-00002.safetensors",
|
| 44 |
+
"norm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"prediction_head.bias": "model-00001-of-00002.safetensors",
|
| 46 |
+
"prediction_head.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"response_selector.bias": "model-00001-of-00002.safetensors",
|
| 48 |
+
"response_selector.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"shared_layer.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"shared_layer.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"shared_layer.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"shared_layer.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"shared_layer.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"shared_layer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"shared_layer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"shared_layer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"shared_layer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"simulation_head.bias": "model-00001-of-00002.safetensors",
|
| 59 |
+
"simulation_head.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"stimuli_vector": "model-00001-of-00002.safetensors",
|
| 61 |
+
"unique_layer.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"unique_layer.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"unique_layer.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"unique_layer.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"unique_layer.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"unique_layer.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"unique_layer.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"unique_layer.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"unique_layer.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
| 70 |
+
}
|
| 71 |
+
}
|