Instructions to use FreedomIntelligence/Apollo-MedJamba with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/Apollo-MedJamba with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/Apollo-MedJamba", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/Apollo-MedJamba", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/Apollo-MedJamba", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FreedomIntelligence/Apollo-MedJamba with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FreedomIntelligence/Apollo-MedJamba

SGLang

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

Docker Model Runner
How to use FreedomIntelligence/Apollo-MedJamba with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/Apollo-MedJamba
```

Xidong commited on Apr 24, 2024

Commit

8f730fc

verified ·

1 Parent(s): 6027891

Upload ./config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +49 -0

config.json ADDED Viewed

	@@ -0,0 +1,49 @@

+{
+  "_name_or_path": "/sds_wangby/models/Jamba-v0.1",
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 4,
+  "attn_layer_period": 8,
+  "auto_map": {
+    "AutoConfig": "configuration_jamba.JambaConfig",
+    "AutoModel": "modeling_jamba.JambaModel",
+    "AutoModelForCausalLM": "modeling_jamba.JambaForCausalLM",
+    "AutoModelForSequenceClassification": "model.JambaForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "calc_logits_for_entire_prompt": false,
+  "eos_token_id": 2,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 256,
+  "mamba_expand": 2,
+  "mamba_inner_layernorms": true,
+  "mamba_proj_bias": false,
+  "model_type": "jamba",
+  "n_ctx": 262144,
+  "num_attention_heads": 32,
+  "num_experts": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 65536
+}