Instructions to use finalform/foamQwen2.5-7B-Instruct-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use finalform/foamQwen2.5-7B-Instruct-fp16 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "finalform/foamQwen2.5-7B-Instruct-fp16")

Transformers

How to use finalform/foamQwen2.5-7B-Instruct-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="finalform/foamQwen2.5-7B-Instruct-fp16")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("finalform/foamQwen2.5-7B-Instruct-fp16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use finalform/foamQwen2.5-7B-Instruct-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "finalform/foamQwen2.5-7B-Instruct-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalform/foamQwen2.5-7B-Instruct-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/finalform/foamQwen2.5-7B-Instruct-fp16

SGLang

How to use finalform/foamQwen2.5-7B-Instruct-fp16 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 "finalform/foamQwen2.5-7B-Instruct-fp16" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalform/foamQwen2.5-7B-Instruct-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "finalform/foamQwen2.5-7B-Instruct-fp16" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "finalform/foamQwen2.5-7B-Instruct-fp16",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use finalform/foamQwen2.5-7B-Instruct-fp16 with Docker Model Runner:
```
docker model run hf.co/finalform/foamQwen2.5-7B-Instruct-fp16
```

finalform commited on Nov 9, 2025

Commit

e5578c9

verified ·

1 Parent(s): 67e05e1

Upload folder using huggingface_hub

Browse files

Files changed (6) hide show

adapter_model.safetensors +1 -1
optimizer.pt +1 -1
rng_state.pth +1 -1
scaler.pt +1 -1
scheduler.pt +1 -1
trainer_state.json +483 -3

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b86b182c79301e2ab23320b6e9b74b467fca5d557f073bfec72e3a33f8672631
 size 645975704

 version https://git-lfs.github.com/spec/v1
+oid sha256:4528ab87f9ce39434c392e7a67cad0fb130753649ef9e5cb24d321781a9bbcfb
 size 645975704

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76394619622fa2e9d668cd68cfb8ff84d6dca42ca4a9720f32e2a997bd2b0698
 size 1292087499

 version https://git-lfs.github.com/spec/v1
+oid sha256:87c7b9c830848e5452e2a2554acbc8ebf215a4ed3446dc4441cc05860a5f82d8
 size 1292087499

rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13edb95449851c4aad8bf0e2144044aabcb2dee5971f11af954476099ec37024
 size 14645

 version https://git-lfs.github.com/spec/v1
+oid sha256:94e1c5b5a299195c16e2136ce4b158c5bef8b18fb216a95951511ee6a27a0e40
 size 14645

scaler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ede48f89e14b189e74a28c0cd4e38a34d5bddbd9429356e0454f7eeb16f0e71
 size 1383

 version https://git-lfs.github.com/spec/v1
+oid sha256:03db65b95f9d6052d21e0bca73ef5811c9250fdf4e71820d48477895469025d8
 size 1383

scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4361ddfd3652d9646a72d7e3e69463d6582550af453e0c12dedcaaac34a5d817
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:951c5397aaebd0765bacaf853fdf43a5f8d077a2f0f518d9f0dba2068e909691
 size 1465

trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1245,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -479,6 +479,486 @@
       "eval_samples_per_second": 10.778,
       "eval_steps_per_second": 5.403,
       "step": 1245
     }
   ],
   "logging_steps": 25,
@@ -498,7 +978,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4162973886316544e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 6.0,
   "eval_steps": 500,
+  "global_step": 2490,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "eval_samples_per_second": 10.778,
       "eval_steps_per_second": 5.403,
       "step": 1245
+    },
+    {
+      "epoch": 3.012070006035003,
+      "grad_norm": 0.019530098885297775,
+      "learning_rate": 0.00032513066101458505,
+      "loss": 0.0106,
+      "mean_token_accuracy": 0.996635879437948,
+      "num_tokens": 10218496.0,
+      "step": 1250
+    },
+    {
+      "epoch": 3.0724200362100182,
+      "grad_norm": 0.014008881524205208,
+      "learning_rate": 0.0003182506174518353,
+      "loss": 0.0106,
+      "mean_token_accuracy": 0.9967661571502685,
+      "num_tokens": 10423296.0,
+      "step": 1275
+    },
+    {
+      "epoch": 3.1327700663850333,
+      "grad_norm": 0.023790989071130753,
+      "learning_rate": 0.0003113217990394111,
+      "loss": 0.0116,
+      "mean_token_accuracy": 0.9965166473388671,
+      "num_tokens": 10628096.0,
+      "step": 1300
+    },
+    {
+      "epoch": 3.1931200965600484,
+      "grad_norm": 0.019647866487503052,
+      "learning_rate": 0.0003043495914147805,
+      "loss": 0.0104,
+      "mean_token_accuracy": 0.9967123413085938,
+      "num_tokens": 10832896.0,
+      "step": 1325
+    },
+    {
+      "epoch": 3.2534701267350634,
+      "grad_norm": 0.031535252928733826,
+      "learning_rate": 0.0002973394139410128,
+      "loss": 0.0105,
+      "mean_token_accuracy": 0.9966634178161621,
+      "num_tokens": 11037696.0,
+      "step": 1350
+    },
+    {
+      "epoch": 3.3138201569100785,
+      "grad_norm": 0.035145845264196396,
+      "learning_rate": 0.00029029671549441144,
+      "loss": 0.0103,
+      "mean_token_accuracy": 0.9967025566101074,
+      "num_tokens": 11242496.0,
+      "step": 1375
+    },
+    {
+      "epoch": 3.3741701870850935,
+      "grad_norm": 0.011679012328386307,
+      "learning_rate": 0.0002832269702292078,
+      "loss": 0.01,
+      "mean_token_accuracy": 0.9966927719116211,
+      "num_tokens": 11447296.0,
+      "step": 1400
+    },
+    {
+      "epoch": 3.4345202172601086,
+      "grad_norm": 0.009404915384948254,
+      "learning_rate": 0.0002761356733226058,
+      "loss": 0.01,
+      "mean_token_accuracy": 0.9966976642608643,
+      "num_tokens": 11652096.0,
+      "step": 1425
+    },
+    {
+      "epoch": 3.4948702474351236,
+      "grad_norm": 0.01060599833726883,
+      "learning_rate": 0.00026902833670348577,
+      "loss": 0.0098,
+      "mean_token_accuracy": 0.9968199729919434,
+      "num_tokens": 11856896.0,
+      "step": 1450
+    },
+    {
+      "epoch": 3.5552202776101387,
+      "grad_norm": 0.011005139909684658,
+      "learning_rate": 0.00026191048476808935,
+      "loss": 0.0101,
+      "mean_token_accuracy": 0.9967221260070801,
+      "num_tokens": 12061696.0,
+      "step": 1475
+    },
+    {
+      "epoch": 3.6155703077851538,
+      "grad_norm": 0.00999362114816904,
+      "learning_rate": 0.0002547876500860108,
+      "loss": 0.0098,
+      "mean_token_accuracy": 0.9968640041351319,
+      "num_tokens": 12266496.0,
+      "step": 1500
+    },
+    {
+      "epoch": 3.675920337960169,
+      "grad_norm": 0.014084997586905956,
+      "learning_rate": 0.0002476653690998382,
+      "loss": 0.0098,
+      "mean_token_accuracy": 0.9968199729919434,
+      "num_tokens": 12471296.0,
+      "step": 1525
+    },
+    {
+      "epoch": 3.736270368135184,
+      "grad_norm": 0.010335746221244335,
+      "learning_rate": 0.00024054917782178188,
+      "loss": 0.0099,
+      "mean_token_accuracy": 0.9967123413085938,
+      "num_tokens": 12676096.0,
+      "step": 1550
+    },
+    {
+      "epoch": 3.796620398310199,
+      "grad_norm": 0.009000259451568127,
+      "learning_rate": 0.0002334446075306396,
+      "loss": 0.0097,
+      "mean_token_accuracy": 0.9969129276275634,
+      "num_tokens": 12880896.0,
+      "step": 1575
+    },
+    {
+      "epoch": 3.856970428485214,
+      "grad_norm": 0.009936418384313583,
+      "learning_rate": 0.00022635718047243897,
+      "loss": 0.0098,
+      "mean_token_accuracy": 0.9967465877532959,
+      "num_tokens": 13085696.0,
+      "step": 1600
+    },
+    {
+      "epoch": 3.9173204586602295,
+      "grad_norm": 0.009142445400357246,
+      "learning_rate": 0.00021929240556810162,
+      "loss": 0.0094,
+      "mean_token_accuracy": 0.9967563724517823,
+      "num_tokens": 13290496.0,
+      "step": 1625
+    },
+    {
+      "epoch": 3.9776704888352445,
+      "grad_norm": 0.011989991180598736,
+      "learning_rate": 0.00021225577413146564,
+      "loss": 0.0096,
+      "mean_token_accuracy": 0.9968640041351319,
+      "num_tokens": 13495296.0,
+      "step": 1650
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.009996045380830765,
+      "eval_mean_token_accuracy": 0.9968979861285235,
+      "eval_num_tokens": 13570048.0,
+      "eval_runtime": 34.2398,
+      "eval_samples_per_second": 10.777,
+      "eval_steps_per_second": 5.403,
+      "step": 1660
+    },
+    {
+      "epoch": 4.036210018105009,
+      "grad_norm": 0.012058747932314873,
+      "learning_rate": 0.0002052527556009917,
+      "loss": 0.0094,
+      "mean_token_accuracy": 0.9968678877525723,
+      "num_tokens": 13692928.0,
+      "step": 1675
+    },
+    {
+      "epoch": 4.096560048280024,
+      "grad_norm": 0.009371360763907433,
+      "learning_rate": 0.00019828879328847448,
+      "loss": 0.0093,
+      "mean_token_accuracy": 0.9968884658813476,
+      "num_tokens": 13897728.0,
+      "step": 1700
+    },
+    {
+      "epoch": 4.15691007845504,
+      "grad_norm": 0.008277242071926594,
+      "learning_rate": 0.00019136930014806037,
+      "loss": 0.0092,
+      "mean_token_accuracy": 0.9968346500396729,
+      "num_tokens": 14102528.0,
+      "step": 1725
+    },
+    {
+      "epoch": 4.217260108630055,
+      "grad_norm": 0.008042911067605019,
+      "learning_rate": 0.00018449965456886262,
+      "loss": 0.009,
+      "mean_token_accuracy": 0.9969080352783203,
+      "num_tokens": 14307328.0,
+      "step": 1750
+    },
+    {
+      "epoch": 4.27761013880507,
+      "grad_norm": 0.010238353163003922,
+      "learning_rate": 0.0001776851961944424,
+      "loss": 0.0092,
+      "mean_token_accuracy": 0.9969129276275634,
+      "num_tokens": 14512128.0,
+      "step": 1775
+    },
+    {
+      "epoch": 4.337960168980085,
+      "grad_norm": 0.009031562134623528,
+      "learning_rate": 0.00017093122177240684,
+      "loss": 0.0093,
+      "mean_token_accuracy": 0.9969667434692383,
+      "num_tokens": 14716928.0,
+      "step": 1800
+    },
+    {
+      "epoch": 4.3983101991551,
+      "grad_norm": 0.0108866598457098,
+      "learning_rate": 0.00016424298103734827,
+      "loss": 0.0091,
+      "mean_token_accuracy": 0.9969080352783203,
+      "num_tokens": 14921728.0,
+      "step": 1825
+    },
+    {
+      "epoch": 4.458660229330115,
+      "grad_norm": 0.00900843646377325,
+      "learning_rate": 0.0001576256726303272,
+      "loss": 0.0093,
+      "mean_token_accuracy": 0.9969324970245361,
+      "num_tokens": 15126528.0,
+      "step": 1850
+    },
+    {
+      "epoch": 4.51901025950513,
+      "grad_norm": 0.008820630609989166,
+      "learning_rate": 0.00015108444005806725,
+      "loss": 0.0093,
+      "mean_token_accuracy": 0.9968835735321044,
+      "num_tokens": 15331328.0,
+      "step": 1875
+    },
+    {
+      "epoch": 4.579360289680145,
+      "grad_norm": 0.009221971966326237,
+      "learning_rate": 0.00014462436769500773,
+      "loss": 0.0091,
+      "mean_token_accuracy": 0.9968933582305908,
+      "num_tokens": 15536128.0,
+      "step": 1900
+    },
+    {
+      "epoch": 4.63971031985516,
+      "grad_norm": 0.010153044946491718,
+      "learning_rate": 0.0001382504768313155,
+      "loss": 0.0092,
+      "mean_token_accuracy": 0.9969031429290771,
+      "num_tokens": 15740928.0,
+      "step": 1925
+    },
+    {
+      "epoch": 4.700060350030175,
+      "grad_norm": 0.009132993407547474,
+      "learning_rate": 0.00013196772176993376,
+      "loss": 0.0093,
+      "mean_token_accuracy": 0.997020559310913,
+      "num_tokens": 15945728.0,
+      "step": 1950
+    },
+    {
+      "epoch": 4.76041038020519,
+      "grad_norm": 0.009844532236456871,
+      "learning_rate": 0.00012578098597569682,
+      "loss": 0.0093,
+      "mean_token_accuracy": 0.9968884658813476,
+      "num_tokens": 16150528.0,
+      "step": 1975
+    },
+    {
+      "epoch": 4.820760410380205,
+      "grad_norm": 0.010243461467325687,
+      "learning_rate": 0.00011969507827950694,
+      "loss": 0.0094,
+      "mean_token_accuracy": 0.9969080352783203,
+      "num_tokens": 16355328.0,
+      "step": 2000
+    },
+    {
+      "epoch": 4.88111044055522,
+      "grad_norm": 0.010576976463198662,
+      "learning_rate": 0.00011371472914052234,
+      "loss": 0.0091,
+      "mean_token_accuracy": 0.9969520664215088,
+      "num_tokens": 16560128.0,
+      "step": 2025
+    },
+    {
+      "epoch": 4.941460470730235,
+      "grad_norm": 0.008221893571317196,
+      "learning_rate": 0.00010784458696926253,
+      "loss": 0.0092,
+      "mean_token_accuracy": 0.9968737888336182,
+      "num_tokens": 16764928.0,
+      "step": 2050
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.02519950643181801,
+      "learning_rate": 0.0001020892145144872,
+      "loss": 0.009,
+      "mean_token_accuracy": 0.996883018729613,
+      "num_tokens": 16962560.0,
+      "step": 2075
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.009800967760384083,
+      "eval_mean_token_accuracy": 0.9968027836567647,
+      "eval_num_tokens": 16962560.0,
+      "eval_runtime": 34.241,
+      "eval_samples_per_second": 10.777,
+      "eval_steps_per_second": 5.403,
+      "step": 2075
+    },
+    {
+      "epoch": 5.060350030175015,
+      "grad_norm": 0.009994215331971645,
+      "learning_rate": 9.645308531666052e-05,
+      "loss": 0.0089,
+      "mean_token_accuracy": 0.9969227123260498,
+      "num_tokens": 17167360.0,
+      "step": 2100
+    },
+    {
+      "epoch": 5.12070006035003,
+      "grad_norm": 0.00914147961884737,
+      "learning_rate": 9.094058023075292e-05,
+      "loss": 0.0087,
+      "mean_token_accuracy": 0.9971526527404785,
+      "num_tokens": 17372160.0,
+      "step": 2125
+    },
+    {
+      "epoch": 5.181050090525045,
+      "grad_norm": 0.008889489807188511,
+      "learning_rate": 8.555598402108725e-05,
+      "loss": 0.009,
+      "mean_token_accuracy": 0.9970107746124267,
+      "num_tokens": 17576960.0,
+      "step": 2150
+    },
+    {
+      "epoch": 5.24140012070006,
+      "grad_norm": 0.009806985966861248,
+      "learning_rate": 8.030348203087353e-05,
+      "loss": 0.009,
+      "mean_token_accuracy": 0.9970596981048584,
+      "num_tokens": 17781760.0,
+      "step": 2175
+    },
+    {
+      "epoch": 5.301750150875075,
+      "grad_norm": 0.009788556955754757,
+      "learning_rate": 7.518715692902254e-05,
+      "loss": 0.009,
+      "mean_token_accuracy": 0.9970352363586426,
+      "num_tokens": 17986560.0,
+      "step": 2200
+    },
+    {
+      "epoch": 5.36210018105009,
+      "grad_norm": 0.010473587550222874,
+      "learning_rate": 7.021098553676493e-05,
+      "loss": 0.0089,
+      "mean_token_accuracy": 0.996927604675293,
+      "num_tokens": 18191360.0,
+      "step": 2225
+    },
+    {
+      "epoch": 5.422450211225105,
+      "grad_norm": 0.011041617952287197,
+      "learning_rate": 6.537883573654501e-05,
+      "loss": 0.0089,
+      "mean_token_accuracy": 0.9969618511199951,
+      "num_tokens": 18396160.0,
+      "step": 2250
+    },
+    {
+      "epoch": 5.4828002414001205,
+      "grad_norm": 0.008172512985765934,
+      "learning_rate": 6.069446346558982e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9970352363586426,
+      "num_tokens": 18600960.0,
+      "step": 2275
+    },
+    {
+      "epoch": 5.5431502715751355,
+      "grad_norm": 0.009114045649766922,
+      "learning_rate": 5.616150979649147e-05,
+      "loss": 0.0089,
+      "mean_token_accuracy": 0.9970548057556152,
+      "num_tokens": 18805760.0,
+      "step": 2300
+    },
+    {
+      "epoch": 5.603500301750151,
+      "grad_norm": 0.008835142478346825,
+      "learning_rate": 5.178349810707104e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9969912052154541,
+      "num_tokens": 19010560.0,
+      "step": 2325
+    },
+    {
+      "epoch": 5.663850331925166,
+      "grad_norm": 0.008637483231723309,
+      "learning_rate": 4.756383134172478e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9970939445495606,
+      "num_tokens": 19215360.0,
+      "step": 2350
+    },
+    {
+      "epoch": 5.724200362100181,
+      "grad_norm": 0.008629810996353626,
+      "learning_rate": 4.3505789366381116e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9970254516601562,
+      "num_tokens": 19420160.0,
+      "step": 2375
+    },
+    {
+      "epoch": 5.784550392275197,
+      "grad_norm": 0.009468801319599152,
+      "learning_rate": 3.9612526419123156e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9969618511199951,
+      "num_tokens": 19624960.0,
+      "step": 2400
+    },
+    {
+      "epoch": 5.844900422450211,
+      "grad_norm": 0.009678692556917667,
+      "learning_rate": 3.5887068658460824e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9969667434692383,
+      "num_tokens": 19829760.0,
+      "step": 2425
+    },
+    {
+      "epoch": 5.905250452625227,
+      "grad_norm": 0.010459608398377895,
+      "learning_rate": 3.2332311811155415e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9969618511199951,
+      "num_tokens": 20034560.0,
+      "step": 2450
+    },
+    {
+      "epoch": 5.965600482800241,
+      "grad_norm": 0.011055945418775082,
+      "learning_rate": 2.8951018921426954e-05,
+      "loss": 0.0088,
+      "mean_token_accuracy": 0.9969667434692383,
+      "num_tokens": 20239360.0,
+      "step": 2475
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.009622456505894661,
+      "eval_mean_token_accuracy": 0.9968900525892103,
+      "eval_num_tokens": 20355072.0,
+      "eval_runtime": 34.2252,
+      "eval_samples_per_second": 10.782,
+      "eval_steps_per_second": 5.405,
+      "step": 2490
     }
   ],
   "logging_steps": 25,
       "attributes": {}
     }
   },
+  "total_flos": 8.832594777263309e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null