Text Generation
Transformers
Safetensors
phi
custom_code
text-generation-inference
8-bit precision
bitsandbytes
Instructions to use rfernand/phi2_ft4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rfernand/phi2_ft4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="rfernand/phi2_ft4", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("rfernand/phi2_ft4", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("rfernand/phi2_ft4", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use rfernand/phi2_ft4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "rfernand/phi2_ft4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rfernand/phi2_ft4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/rfernand/phi2_ft4
- SGLang
How to use rfernand/phi2_ft4 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 "rfernand/phi2_ft4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rfernand/phi2_ft4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "rfernand/phi2_ft4" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "rfernand/phi2_ft4", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use rfernand/phi2_ft4 with Docker Model Runner:
docker model run hf.co/rfernand/phi2_ft4
Upload PhiForCausalLM
Browse files- config.json +48 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/phi-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
| 9 |
+
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
| 10 |
+
},
|
| 11 |
+
"bos_token_id": 50256,
|
| 12 |
+
"embd_pdrop": 0.0,
|
| 13 |
+
"eos_token_id": 50256,
|
| 14 |
+
"hidden_act": "gelu_new",
|
| 15 |
+
"hidden_size": 2560,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 10240,
|
| 18 |
+
"layer_norm_eps": 1e-05,
|
| 19 |
+
"max_position_embeddings": 2048,
|
| 20 |
+
"model_type": "phi",
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_hidden_layers": 32,
|
| 23 |
+
"num_key_value_heads": 32,
|
| 24 |
+
"partial_rotary_factor": 0.4,
|
| 25 |
+
"qk_layernorm": false,
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"_load_in_4bit": false,
|
| 28 |
+
"_load_in_8bit": true,
|
| 29 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 30 |
+
"bnb_4bit_quant_type": "fp4",
|
| 31 |
+
"bnb_4bit_use_double_quant": false,
|
| 32 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 33 |
+
"llm_int8_has_fp16_weight": false,
|
| 34 |
+
"llm_int8_skip_modules": null,
|
| 35 |
+
"llm_int8_threshold": 6.0,
|
| 36 |
+
"load_in_4bit": false,
|
| 37 |
+
"load_in_8bit": true,
|
| 38 |
+
"quant_method": "bitsandbytes"
|
| 39 |
+
},
|
| 40 |
+
"resid_pdrop": 0.1,
|
| 41 |
+
"rope_scaling": null,
|
| 42 |
+
"rope_theta": 10000.0,
|
| 43 |
+
"tie_word_embeddings": false,
|
| 44 |
+
"torch_dtype": "float16",
|
| 45 |
+
"transformers_version": "4.39.0.dev0",
|
| 46 |
+
"use_cache": false,
|
| 47 |
+
"vocab_size": 51200
|
| 48 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.39.0.dev0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2abe84b1122828bb312dedba64f42c5f764f648665277ab5ecea2160b93623d7
|
| 3 |
+
size 3072034176
|