Instructions to use miguel-kjh/pythia-70m_instruction_code_tuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use miguel-kjh/pythia-70m_instruction_code_tuning with Transformers:

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

pipe = pipeline("text-generation", model="miguel-kjh/pythia-70m_instruction_code_tuning")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("miguel-kjh/pythia-70m_instruction_code_tuning")
model = AutoModelForCausalLM.from_pretrained("miguel-kjh/pythia-70m_instruction_code_tuning")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use miguel-kjh/pythia-70m_instruction_code_tuning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "miguel-kjh/pythia-70m_instruction_code_tuning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "miguel-kjh/pythia-70m_instruction_code_tuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/miguel-kjh/pythia-70m_instruction_code_tuning

SGLang

How to use miguel-kjh/pythia-70m_instruction_code_tuning 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 "miguel-kjh/pythia-70m_instruction_code_tuning" \
    --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": "miguel-kjh/pythia-70m_instruction_code_tuning",
		"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 "miguel-kjh/pythia-70m_instruction_code_tuning" \
        --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": "miguel-kjh/pythia-70m_instruction_code_tuning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use miguel-kjh/pythia-70m_instruction_code_tuning with Docker Model Runner:
```
docker model run hf.co/miguel-kjh/pythia-70m_instruction_code_tuning
```

miguel-kjh commited on Jul 3, 2024

Commit

6325109

verified ·

1 Parent(s): 476f708

Upload GPTNeoXForCausalLM

Browse files

Files changed (2) hide show

config.json +16 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -19,11 +19,26 @@
   "num_attention_heads": 8,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "use_parallel_residual": true,

   "num_attention_heads": 8,
   "num_hidden_layers": 6,
   "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
+  "torch_dtype": "float16",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "use_parallel_residual": true,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3549d3d2a785b94af370c0d0dfa9e4c464b85baba7c03d4e5ee1cb0baa7736
-size 281715176

 version https://git-lfs.github.com/spec/v1
+oid sha256:f412b68b0502219928444040879b846679572d2e233599fefc3035dfcda21ea3
+size 113742442