Instructions to use Den4ikAI/instruct_medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Den4ikAI/instruct_medium with Transformers:

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

pipe = pipeline("text-generation", model="Den4ikAI/instruct_medium")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Den4ikAI/instruct_medium")
model = AutoModelForCausalLM.from_pretrained("Den4ikAI/instruct_medium", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Den4ikAI/instruct_medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Den4ikAI/instruct_medium"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Den4ikAI/instruct_medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Den4ikAI/instruct_medium

SGLang

How to use Den4ikAI/instruct_medium 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 "Den4ikAI/instruct_medium" \
    --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": "Den4ikAI/instruct_medium",
		"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 "Den4ikAI/instruct_medium" \
        --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": "Den4ikAI/instruct_medium",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Den4ikAI/instruct_medium with Docker Model Runner:
```
docker model run hf.co/Den4ikAI/instruct_medium
```

Den4ikAI commited on Mar 7, 2023

Commit

fb86e70

1 Parent(s): e5b9126

Upload 6 files

Browse files

Files changed (6) hide show

config.json +2 -6
eval_results.json +9 -0
merges.txt +1 -1
special_tokens_map.json +1 -1
tokenizer_config.json +1 -1
vocab.json +0 -0

config.json CHANGED Viewed

@@ -1,9 +1,5 @@
 {
-  "_name_or_path": "model",
   "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
@@ -36,7 +32,7 @@
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.11.3",
   "use_cache": true,
-  "vocab_size": 50262
 }

 {
   "activation_function": "gelu_new",
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "summary_type": "cls_index",
   "summary_use_proj": true,
   "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
   "use_cache": true,
+  "vocab_size": 50261
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 1.0,
+    "eval_loss": 3.4997777938842773,
+    "eval_runtime": 448.829,
+    "eval_samples": 40311,
+    "eval_samples_per_second": 89.814,
+    "eval_steps_per_second": 7.486,
+    "perplexity": 33.10809432022858
+}

merges.txt CHANGED Viewed

@@ -1,4 +1,4 @@
-#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ Ð
 Ð ¾
 Ð µ

+#version: 0.2
 Ġ Ð
 Ð ¾
 Ð µ

special_tokens_map.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>"}


1	+ {"bos_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<\|endoftext\|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<pad>"}

tokenizer_config.json CHANGED Viewed

@@ -1 +1 @@

- {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "~~errors": "replace", "~~special_tokens_map_file": null, "use_fast": true, "~~name_or_path": "model", "~~tokenizer_class": "GPT2Tokenizer"}

+ {"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "use_fast": true, "tokenizer_class": "GPT2Tokenizer"}

vocab.json CHANGED Viewed

The diff for this file is too large to render. See raw diff