Instructions to use CryptAL/tm3B1_gemma2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CryptAL/tm3B1_gemma2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CryptAL/tm3B1_gemma2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CryptAL/tm3B1_gemma2") model = AutoModelForCausalLM.from_pretrained("CryptAL/tm3B1_gemma2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use CryptAL/tm3B1_gemma2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CryptAL/tm3B1_gemma2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CryptAL/tm3B1_gemma2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CryptAL/tm3B1_gemma2
- SGLang
How to use CryptAL/tm3B1_gemma2 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 "CryptAL/tm3B1_gemma2" \ --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": "CryptAL/tm3B1_gemma2", "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 "CryptAL/tm3B1_gemma2" \ --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": "CryptAL/tm3B1_gemma2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CryptAL/tm3B1_gemma2 with Docker Model Runner:
docker model run hf.co/CryptAL/tm3B1_gemma2
Upload Gemma2ForCausalLM
Browse files- config.json +2 -2
- generation_config.json +2 -2
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
config.json
CHANGED
|
@@ -6,9 +6,9 @@
|
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"attn_logit_softcapping": 50.0,
|
| 9 |
-
"bos_token_id":
|
| 10 |
"cache_implementation": "hybrid",
|
| 11 |
-
"eos_token_id":
|
| 12 |
"final_logit_softcapping": 30.0,
|
| 13 |
"head_dim": 256,
|
| 14 |
"hidden_act": "gelu_pytorch_tanh",
|
|
|
|
| 6 |
"attention_bias": false,
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"attn_logit_softcapping": 50.0,
|
| 9 |
+
"bos_token_id": 100257,
|
| 10 |
"cache_implementation": "hybrid",
|
| 11 |
+
"eos_token_id": 100257,
|
| 12 |
"final_logit_softcapping": 30.0,
|
| 13 |
"head_dim": 256,
|
| 14 |
"hidden_act": "gelu_pytorch_tanh",
|
generation_config.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"bos_token_id":
|
| 4 |
"cache_implementation": "hybrid",
|
| 5 |
-
"eos_token_id":
|
| 6 |
"pad_token_id": 0,
|
| 7 |
"transformers_version": "4.42.0"
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
"cache_implementation": "hybrid",
|
| 5 |
+
"eos_token_id": 100257,
|
| 6 |
"pad_token_id": 0,
|
| 7 |
"transformers_version": "4.42.0"
|
| 8 |
}
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4995172192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a915b067345e531cd264ec5031480d602b7335fee04f8b90d2aa6177fd3a8c5e
|
| 3 |
size 4995172192
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1786265872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f1c3d111c966095d427f60a255ca3161708b91d6d0da59971d50db361a70e86
|
| 3 |
size 1786265872
|