Instructions to use CryptAL/tm3B1_phi3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CryptAL/tm3B1_phi3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CryptAL/tm3B1_phi3")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("CryptAL/tm3B1_phi3") model = AutoModelForCausalLM.from_pretrained("CryptAL/tm3B1_phi3") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use CryptAL/tm3B1_phi3 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CryptAL/tm3B1_phi3" # 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_phi3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CryptAL/tm3B1_phi3
- SGLang
How to use CryptAL/tm3B1_phi3 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_phi3" \ --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_phi3", "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_phi3" \ --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_phi3", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CryptAL/tm3B1_phi3 with Docker Model Runner:
docker model run hf.co/CryptAL/tm3B1_phi3
Upload Phi3ForCausalLM
Browse files- config.json +2 -2
- model-00001-of-00002.safetensors +2 -2
- model-00002-of-00002.safetensors +2 -2
- model.safetensors.index.json +43 -43
config.json
CHANGED
|
@@ -8,9 +8,9 @@
|
|
| 8 |
"embd_pdrop": 0.0,
|
| 9 |
"eos_token_id": 100257,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
-
"hidden_size":
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
-
"intermediate_size":
|
| 14 |
"max_position_embedding": 4096,
|
| 15 |
"max_position_embeddings": 4096,
|
| 16 |
"model_type": "phi3",
|
|
|
|
| 8 |
"embd_pdrop": 0.0,
|
| 9 |
"eos_token_id": 100257,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2784,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 6700,
|
| 14 |
"max_position_embedding": 4096,
|
| 15 |
"max_position_embeddings": 4096,
|
| 16 |
"model_type": "phi3",
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0cce87bb7bc2be45e0cee964e14530f9f9c3284a983b338dadc6d7deaeba1f0
|
| 3 |
+
size 4968756344
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:780d30939b5ce6870101d2437abedfeb79e5e4289585d908a11c8db97595876d
|
| 3 |
+
size 1713941080
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
@@ -65,60 +65,60 @@
|
|
| 65 |
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
"model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
-
"model.layers.18.input_layernorm.weight": "model-
|
| 69 |
-
"model.layers.18.mlp.down_proj.weight": "model-
|
| 70 |
-
"model.layers.18.mlp.gate_up_proj.weight": "model-
|
| 71 |
-
"model.layers.18.post_attention_layernorm.weight": "model-
|
| 72 |
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
-
"model.layers.19.input_layernorm.weight": "model-
|
| 75 |
-
"model.layers.19.mlp.down_proj.weight": "model-
|
| 76 |
-
"model.layers.19.mlp.gate_up_proj.weight": "model-
|
| 77 |
-
"model.layers.19.post_attention_layernorm.weight": "model-
|
| 78 |
-
"model.layers.19.self_attn.o_proj.weight": "model-
|
| 79 |
-
"model.layers.19.self_attn.qkv_proj.weight": "model-
|
| 80 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
-
"model.layers.20.input_layernorm.weight": "model-
|
| 87 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
| 88 |
-
"model.layers.20.mlp.gate_up_proj.weight": "model-
|
| 89 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
| 90 |
-
"model.layers.20.self_attn.o_proj.weight": "model-
|
| 91 |
-
"model.layers.20.self_attn.qkv_proj.weight": "model-
|
| 92 |
-
"model.layers.21.input_layernorm.weight": "model-
|
| 93 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
| 94 |
-
"model.layers.21.mlp.gate_up_proj.weight": "model-
|
| 95 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
| 96 |
-
"model.layers.21.self_attn.o_proj.weight": "model-
|
| 97 |
-
"model.layers.21.self_attn.qkv_proj.weight": "model-
|
| 98 |
-
"model.layers.22.input_layernorm.weight": "model-
|
| 99 |
-
"model.layers.22.mlp.down_proj.weight": "model-
|
| 100 |
-
"model.layers.22.mlp.gate_up_proj.weight": "model-
|
| 101 |
-
"model.layers.22.post_attention_layernorm.weight": "model-
|
| 102 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
| 103 |
-
"model.layers.22.self_attn.qkv_proj.weight": "model-
|
| 104 |
-
"model.layers.23.input_layernorm.weight": "model-
|
| 105 |
-
"model.layers.23.mlp.down_proj.weight": "model-
|
| 106 |
-
"model.layers.23.mlp.gate_up_proj.weight": "model-
|
| 107 |
-
"model.layers.23.post_attention_layernorm.weight": "model-
|
| 108 |
-
"model.layers.23.self_attn.o_proj.weight": "model-
|
| 109 |
-
"model.layers.23.self_attn.qkv_proj.weight": "model-
|
| 110 |
-
"model.layers.24.input_layernorm.weight": "model-
|
| 111 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
| 112 |
-
"model.layers.24.mlp.gate_up_proj.weight": "model-
|
| 113 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
| 114 |
-
"model.layers.24.self_attn.o_proj.weight": "model-
|
| 115 |
-
"model.layers.24.self_attn.qkv_proj.weight": "model-
|
| 116 |
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
-
"model.layers.25.self_attn.o_proj.weight": "model-
|
| 121 |
-
"model.layers.25.self_attn.qkv_proj.weight": "model-
|
| 122 |
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 123 |
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 124 |
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 6682674624
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00002-of-00002.safetensors",
|
|
|
|
| 65 |
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 66 |
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
"model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
"model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
"model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
"model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.20.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.21.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.21.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.22.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.22.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.23.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.23.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.24.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.24.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
"model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
+
"model.layers.25.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 123 |
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 124 |
"model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
|