Skip to content

Commit

Permalink
Add qwen2.5-coder 0.5B 1.5B 3B 14B 32B
Browse files Browse the repository at this point in the history
  • Loading branch information
@frostyplanet
frostyplanet committed Nov 12, 2024
1 parent fe94552 commit 6057081
Show file tree
Hide file tree
Showing 2 changed files with 281 additions and 2 deletions.
133 changes: 131 additions & 2 deletions xinference/model/llm/llm_family.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8205,6 +8205,17 @@
],
"model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": "0_5",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B",
"model_revision": "master"
},
{
"model_format": "pytorch",
"model_size_in_billions": "1_5",
Expand All @@ -8214,7 +8225,18 @@
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B",
"model_revision": "d3586cfe793730945f8e4d7ef31032a3ee50247d"
"model_revision": "master"
},
{
"model_format": "pytorch",
"model_size_in_billions": "3",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-3B",
"model_revision": "master"
},
{
"model_format": "pytorch",
Expand All @@ -8225,7 +8247,29 @@
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-7B",
"model_revision": "30b6a7e874a78d46b80fa1db3194ea427dd41b08"
"model_revision": "master"
},
{
"model_format": "pytorch",
"model_size_in_billions": 14,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-14B",
"model_revision": "master"
},
{
"model_format": "pytorch",
"model_size_in_billions": 32,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-32B",
"model_revision": "master"
}
]
},
Expand All @@ -8243,6 +8287,16 @@
],
"model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": "0_5",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": "1_5",
Expand All @@ -8253,6 +8307,16 @@
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": "3",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-3B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": 7,
Expand All @@ -8263,6 +8327,53 @@
],
"model_id": "Qwen/Qwen2.5-Coder-7B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": 14,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-14B-Instruct"
},
{
"model_format": "pytorch",
"model_size_in_billions": 32,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
},
{
"model_format": "gptq",
"model_size_in_billions": "0_5",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "1_5",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "3",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "7",
Expand All @@ -8272,6 +8383,24 @@
],
"model_id": "Qwen/Qwen2.5-Coder-7B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "14",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "gptq",
"model_size_in_billions": "32",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "Qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-{quantization}"
},
{
"model_format": "ggufv2",
"model_size_in_billions": "1_5",
Expand Down
150 changes: 150 additions & 0 deletions xinference/model/llm/llm_family_modelscope.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5907,6 +5907,18 @@
],
"model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": "0_5",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-0.5B",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": "1_5",
Expand All @@ -5919,6 +5931,18 @@
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": "3",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-3B",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": 7,
Expand All @@ -5930,6 +5954,30 @@
"model_id": "qwen/Qwen2.5-Coder-7B",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": 14,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-14B",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": 32,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-32B",
"model_revision": "master",
"model_hub": "modelscope"
}
]
},
Expand All @@ -5947,6 +5995,18 @@
],
"model_description": "Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen).",
"model_specs": [
{
"model_format": "pytorch",
"model_size_in_billions": "0_5",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-0.5B-Instruct",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": "1_5",
Expand All @@ -5958,6 +6018,17 @@
"model_id": "qwen/Qwen2.5-Coder-1.5B-Instruct",
"model_revision": "master",
"model_hub": "modelscope"
}, {
"model_format": "pytorch",
"model_size_in_billions": "3",
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-3B-Instruct",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
Expand All @@ -5971,6 +6042,63 @@
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": 14,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-14B-Instruct",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "pytorch",
"model_size_in_billions": 32,
"quantizations": [
"4-bit",
"8-bit",
"none"
],
"model_id": "qwen/Qwen2.5-Coder-32B-Instruct",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "gptq",
"model_size_in_billions": "0_5",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "qwen/Qwen2.5-Coder-0.5B-Instruct-GPTQ-{quantization}",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "gptq",
"model_size_in_billions": "1_5",
"quantizations": [
"Int4",
"Int8"
],
"model_id": "qwen/Qwen2.5-Coder-1.5B-Instruct-GPTQ-{quantization}",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "gptq",
"model_size_in_billions": 3,
"quantizations": [
"Int4",
"Int8"
],
"model_id": "qwen/Qwen2.5-Coder-3B-Instruct-GPTQ-{quantization}",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "gptq",
"model_size_in_billions": 7,
Expand All @@ -5982,6 +6110,28 @@
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "gptq",
"model_size_in_billions": 14,
"quantizations": [
"Int4",
"Int8"
],
"model_id": "qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-{quantization}",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "gptq",
"model_size_in_billions": 32,
"quantizations": [
"Int4",
"Int8"
],
"model_id": "qwen/Qwen2.5-Coder-32B-Instruct-GPTQ-{quantization}",
"model_revision": "master",
"model_hub": "modelscope"
},
{
"model_format": "ggufv2",
"model_size_in_billions": "1_5",
Expand Down

0 comments on commit 6057081

Please sign in to comment.